Multi-cue onboard pedestrian detection
The DOI matches its Crossref record; 36 of the 37 references it cites were found in a registry or an index.
Abstract
Various powerful people detection methods exist. Surprisingly, most approaches rely on static image features only despite the obvious potential of motion information for people detection. This paper systematically evaluates different features and classifiers in a sliding-window framework. First, our experiments indicate that incorporating motion information improves detection performance significantly. Second, the combination of multiple and complementary feature types can also help improve performance. And third, the choice of the classifier-feature combination and several implementation details are crucial to reach best performance. In contrast to many recent papers experimental results are reported for four different datasets rather than using a single one. Three of them are taken from the literature allowing for direct comparison. The fourth dataset is newly recorded using an onboard camera driving through urban environment. Consequently this dataset is more realistic and more challenging than any currently available dataset.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 5×
“Dalal et al. [6] enrich their static feature descriptor [ 5 ] with internal motion histograms to improve detection.”
BackgroundMethodResultInfluentialThe Ecological Approach to Visual Perception
Bornstein, M. H., & Gibson, J. J. (1980) · The Journal of Aesthetics and Art Criticism · doi:10.2307/429816 · Cited by 22,935 · cited 1×
“While psychologists and neuroscientists argue that motion is an important cue for human perception [17] only few computer vision object detectors (e.g. [30, 6]) exploit this fact.”
BackgroundRobust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097
Friedman, J., Hastie, T., & Tibshirani, R. (2000) · The Annals of Statistics · doi:10.1214/aos/1016218223 · Cited by 6,884 · cited 1×
“AdaBoost Contrary to SVMs, boosting algorithms [14] optimize the classification error on the training samples iteratively.”
MethodA discriminatively trained, multiscale, deformable part model
Felzenszwalb, P., McAllester, D., & Ramanan, D. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587597 · Cited by 2,867 · cited 2×
“Popular classifiers are SVMs [26, 5, 13, 20, 19] or boosting [31, 7, 33, 23].”
BackgroundDetecting Pedestrians Using Patterns of Motion and Appearance
Viola, P., Jones, M. J., & Snow, D. (2005) · International Journal of Computer Vision · doi:10.1007/s11263-005-6644-8 · Cited by 2,079
A Duality Based Approach for Realtime TV-L 1 Optical Flow
Zach, C., Pock, T., & Bischof, H. (2007) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-74936-3_22 · Cited by 1,658 · cited 2×
“de Objectives Detect pedestrians from a moving platform • Exploit motion information • Leverage complementarity of features • Evaluate different classifiers • New datasets with image pairs Features • HOG [1] 8× 8 pixel cells, 2× 2 blocks 9-bin histograms, unsigned gradients • Haar wavelets [2] 32 and 16 pixel masks ho…”
BackgroundHuman Detection Using Oriented Histograms of Flow and Appearance
Dalal, N., Triggs, B., & Schmid, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744047_33 · Cited by 1,652 · cited 7×
“In contrast, [ 6 ] proposed motion features that are ‐ at least in principle ‐ applicable to onboard sequences.”
BackgroundMethodResultInfluentialPedestrian detection: A benchmark
Dollar, P., Wojek, C., Schiele, B., & Perona, P. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206631 · Cited by 1,313 · cited 3×
“Doll´ ar et al. [ 8 ] report results for various recent approaches on a new challenging onboard dataset with improved evaluation metrics.”
BackgroundInfluentialSelf-citationA Trainable System for Object Detection
Papageorgiou, C., & Poggio, T. (2000) · International Journal of Computer Vision · doi:10.1023/a:1008162616689 · Cited by 1,289 · cited 3×
“Haar Haar wavelets have been introduced by Papageor-giou&Poggio [22] for people detection.”
BackgroundMethodInfluential
Research works printed but not linked: 1
- maji, 2008, Classification using intersection kernel SVMs is efficient, CVPR
Cited by
nuScenes: A Multimodal Dataset for Autonomous Driving
Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01164 · Cited by 7,152
“Other datasets focus exclusively on pedestrian annotations on images [20, 25, 79, 24, 88, 23, 58].”
BackgroundScalable Person Re-identification: A Benchmark
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., & Tian, Q. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.133 · Cited by 4,506
“For other datasets, the codebook is trained on the independent TUD-Brussels dataset [35].”
MethodPedestrian Detection: An Evaluation of the State of the Art
Dollar, P., Wojek, C., Schiele, B., & Perona, P. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.155 · Cited by 3,190
“Pedestrians can be labeled in photographs [7], [16], surveillance video [17], [24], and images taken from a mobile recording setup, such as a robot or vehicle [4], [5], [6].”
BackgroundMethodInfluentialSelf-citationFast Feature Pyramids for Object Detection
Dollar, P., Appel, R., Belongie, S., & Perona, P. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2300479 · Cited by 1,955
“We show results for both pedestrian detection (measured on the Caltech [31], INRIA [21], TUD- Brussels [36] and ETH [37] data sets) and general object detection (measured on the PASCAL VOC [38]).”
MethodA Survey of Deep Learning-Based Object Detection
Jiao, L., Zhang, F., Liu, F., Yang, S., Li, L., Feng, Z., & Qu, R. (2019) · IEEE Access · doi:10.1109/access.2019.2939201 · Cited by 1,323
“TUD-Brussels[57] mobile 1776 218 1092 1498 508”
CityPersons: A Diverse Dataset for Pedestrian Detection
Zhang, S., Benenson, R., & Schiele, B. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.474 · Cited by 1,061
“INRIA [7], ETH [11], TudBrussels [29], and Daimler [10] represent early efforts to collect pedestrian datasets.”
BackgroundSelf-citationSurvey of Pedestrian Detection for Advanced Driver Assistance Systems
Gerónimo, D., López, A. M., Sappa, A. D., & Graf, T. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.122 · Cited by 974
“personal communication with the authors [142], [143].”
Making Bertha Drive—An Autonomous Journey on a Historic Route
Ziegler, J., Bender, P., Schreiber, M., Lategahn, H., Strauss, T., Stiller, C., Dang, T., Franke, U., Appenrodt, N., Keller, C. G., et al. (2014) · IEEE Intelligent Transportation Systems Magazine · doi:10.1109/mits.2014.2306552 · Cited by 854
“An autonomous system, however, requires the environment perception module to detect nearly all obstacles and — at the same time — to have an extremely low false-positive rate.”
BackgroundUA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking
Wen, L., Du, D., Cai, Z., Lei, Z., Chang, M.-C., Qi, H., Lim, J., Yang, M.-H., & Lyu, S. (2020) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2020.102907 · Cited by 804
“9k ! D P 2008 TUD-B (Wojek et al., 2009) 1.”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art
Janai, J., Güney, F., Behl, A., & Geiger, A. (2020) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000079 · Cited by 643
Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes
Hinterstoisser, S., Holzer, S., Cagniart, C., Ilic, S., Konolige, K., Navab, N., & Lepetit, V. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126326 · Cited by 643
“Two main categories can be distinguished: those applied to intensity images and those working on range data or depth images.”
BackgroundGradient Response Maps for Real-Time Detection of Textureless Objects
Hinterstoisser, S., Cagniart, C., Ilic, S., Sturm, P., Navab, N., Fua, P., & Lepetit, V. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.206 · Cited by 610
The Fastest Pedestrian Detector in the West
Dollar, P., Belongie, S., & Perona, P. (2010) · Procedings of the British Machine Vision Conference 2010 · doi:10.5244/c.24.68 · Cited by 571
“The resulting method achieves state-of-the-art results, being within 1-2% detection rate of the highest reported results across four datasets (Caltech Pedestrians [8], INRIA [6], ETH [11], and TUD-Brussels [33]).”
BackgroundMethodTen Years of Pedestrian Detection, What Have We Learned?
Benenson, R., Omran, M., Hosang, J., & Schiele, B. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-16181-5_47 · Cited by 558
“Multiple public pedestrian datasets have been collected over the years; INRIA [1], ETH [2], TUD-Brussels [3], Daimler [4] (Daimler stereo [5]), Caltech-USA [6], and KITTI [7] are the most commonly used ones.”
BackgroundSelf-citationEnd-to-End People Detection in Crowded Scenes
Stewart, R., Andriluka, M., & Ng, A. Y. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.255 · Cited by 539
“the TUD-Brussels dataset [26] as the TUD-Crossing dataset does not provide a corresponding training set 4.”
MethodCrowdHuman: A Benchmark for Detecting Human in a Crowd
Shao, S., Zhao, Z., Li, B., Xiao, T., Yu, G., Zhang, X., & Sun, J. (2018) · arXiv · doi:10.48550/arxiv.1805.00123 · Cited by 534
“ection, COCOPerson for person detection, and Brainwash for head detection. 2. Related Work 2.1. Human detection datasets. Pioneer works of pedestrian detection datasets involve INRIA [3], TudBrussels [27], and Daimler [7]. These datasets have contributed to spurring interest and progress of human detection, However, a…”
BackgroundInfluentialMonocular 3D pose estimation and tracking by detection
Andriluka, M., Roth, S., & Schiele, B. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540156 · Cited by 508
“Front Front”
BackgroundSelf-citationNew features and insights for pedestrian detection
Walk, S., Majer, N., Schindler, K., & Schiele, B. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540102 · Cited by 460
“A similar observation was made by [27], who found that adding Haar features can sometimes help, but careful normalization is required, if the imaging conditions vary.”
BackgroundMethodInfluentialSelf-citationScale Match for Tiny Person Detection
Yu, X., Gong, Y., Jiang, N., Ye, Q., & Han, Z. (2020) · 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv45572.2020.9093394 · Cited by 402
“The scenarios of existing person/pedestrian benchmarks [2][6][24][5][4][8] e.g., CityPersons [27], are mainly in a near or middle distance.”
Effective Fusion Factor in FPN for Tiny Object Detection
Gong, Y., Yu, X., Ding, Y., Peng, X., Zhao, J., & Han, Z. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00120 · Cited by 323
“[4, 8, 31, 7, 6, 10, 34] are scene-rich and well-annotated datasets used for pedestrian detection task.”
BackgroundPedestrian Detection at Day/Night Time with Visible and FIR Cameras: A Comparison
González, A., Fang, Z., Socarras, Y., Serrat, J., Vázquez, D., Xu, J., & López, A. (2016) · Sensors · doi:10.3390/s16060820 · Cited by 322
EuroCity Persons: A Novel Benchmark for Person Detection in Traffic Scenes
Braun, M., Krebs, S., Flohr, F., & Gavrila, D. M. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2897684 · Cited by 307
“Daimler-DB [11], INRIA [19], ETH [20], and TUDBrussels [21]).”
BackgroundInformed Haar-Like Features Improve Pedestrian Detection
Zhang, S., Bauckhage, C., & Cremers, A. B. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.126 · Cited by 299
“A noticeable trend in this domain is that researchers increasingly rely on huge feature pools and high dimensional feature vectors [27] since it is commonly believed that more features integrate more information and thus lead to better performances.”
BackgroundA discriminative deep model for pedestrian detection with occlusion handling
Ouyang, W., & Wang, X. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248062 · Cited by 281
“This dataset contains 1063 images from the datasets of Caltech, ETHZ, TUD-Brussels, INRIA, Caviar and our recorded images from surveillance cameras.”
MethodFused DNN: A Deep Neural Network Fusion Approach to Fast and Robust Pedestrian Detection
Du, X., El-Khamy, M., Lee, J., & Davis, L. (2017) · 2017 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2017.111 · Cited by 273
“To train the SSD candidate generator, all images which contain at least one annotated pedestrian from Caltech training set, ETH dataset [10], and TudBrussels dataset [29] are used.”
MethodHuman detection from images and videos: A survey
Nguyen, D. T., Li, W., & Ogunbona, P. O. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2015.08.027 · Cited by 267
“For the use of optical flow, in [23, 167], histograms of flows (HOF) computed based on differential flows in a similar manner with the HOG [22] were used to describe the boundary motions as well as internal/relative motions (see Figure 2.”
BackgroundMethodSeeking the Strongest Rigid Detector
Benenson, R., Mathias, M., Tuytelaars, T., & Van Gool, L. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.470 · Cited by 253
“It has been previously shown how different boosting approaches give different results [5, 17].”
ResultWILDTRACK: A Multi-camera HD Dataset for Dense Unscripted Pedestrian Detection
Chavdarova, T., Baque, P., Bouquet, S., Maksai, A., Jose, C., Bagautdinov, T., Lettry, L., Fua, P., Van Gool, L., & Fleuret, F. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00528 · Cited by 221
“TUD-Brussels [46] 7720×576; 640×480; 1 1 M n/a Yes 1776+1326 (pos.”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art
Janai, J., Güney, F., Behl, A., & Geiger, A. (2020) · doi:10.1561/9781680836899 · Cited by 232
Real-Time Pedestrian Detection with Deep Network Cascades
Angelova, A., Krizhevsky, A., Vanhoucke, V., Ogale, A., & Ferguson, D. (2015) · Procedings of the British Machine Vision Conference 2015 · doi:10.5244/c.29.32 · Cited by 239
“Pedestrian detection methods have employed a variety of techniques and features [4, 5, 11, 12, 33, 38, 39, 42].”
BackgroundMethodGuo, J., Kurup, U., & Shah, M. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2926042 · Cited by 221
Multiresolution Models for Object Detection
Park, D., Ramanan, D., & Fowlkes, C. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_18 · Cited by 234
“Recent work has focused on models for handling pose variation [15, 11, 16–18], reducing complexity of learning [19, 20]), and multicue combination [21, 22].”
BackgroundMulti-cue pedestrian classification with partial occlusion handling
Enzweiler, M., Eigenstetter, A., Schiele, B., & Gavrila, D. M. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540111 · Cited by 233
“As baseline classifiers, we evaluate the full-body HOG approach of [2] (we use the code provided by the original authors) and the approach of [26], which uses an occlusion model based on the block-wise response of a full-body HOG classifier to activate part-based classifiers in areas corresponding to non-occluded pede…”
BackgroundInfluentialSelf-citationWiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild
Zhang, S., Xie, Y., Wan, J., Xia, H., Li, S. Z., & Guo, G. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2929005 · Cited by 222
“The TUD-Brussels dataset [19] contains image pairs recorded in a crowded urban setting with an onboard camera.”
MethodSharma, V. K., & Mir, R. N. (2020) · Computer Science Review · doi:10.1016/j.cosrev.2020.100301 · Cited by 221
Towards Reaching Human Performance in Pedestrian Detection
Zhang, S., Benenson, R., Omran, M., Hosang, J., & Schiele, B. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2700460 · Cited by 191
“Caltech-USA [15] mobile p 122 k 155 k KITTI [20] mobile p 7,518 INRIA [10] photo p 288 566 ETH [17] mobile p 1,804 12 k TUD-Brussels [44] mobile p 508 1498 Daimler [16] mobile 21.”
BackgroundSelf-citationA General Framework for Tracking Multiple People from a Moving Camera
Choi, W., Pantofaru, C., & Savarese, S. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.248 · Cited by 183
“In this section, we discuss the related work designed to overcome one or more of these challenges.”
Virtual and Real World Adaptation for Pedestrian Detection
Vazquez, D., Lopez, A. M., Marin, J., Ponsa, D., & Geronimo, D. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.163 · Cited by 178
Patch to the Future: Unsupervised Visual Prediction
Walker, J., Gupta, A., & Hebert, M. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.416 · Cited by 179
“For this experiment, since the (a) Original Image (b) Prediction Heatmap”
MethodRobust Multi-resolution Pedestrian Detection in Traffic Scenes
Yan, J., Zhang, X., Lei, Z., Liao, S., & Li, S. Z. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.390 · Cited by 167
“There are some papers fused HOG with other features [43, 7, 45, 41] to improve the performance.”
BackgroundFrom Handcrafted to Deep Features for Pedestrian Detection: A Survey
Cao, J., Pang, Y., Xie, J., Khan, F. S., & Shao, L. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3076733 · Cited by 160
“TUD-Brussels [203] is recorded from a driving car in the city of Brussels and contains 508 images at a fixed resolution of 650×480 pixels.”
BackgroundGeneralizable Pedestrian Detection: The Elephant In The Room
Hasan, I., Liao, S., Li, J., Akram, S. U., & Shao, L. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01117 · Cited by 189
“s. Pedestriandetectionbenchmarks. Over the years, several datasets for pedestrian detection have been created such as Town Center [3], USC [42], Daimler-DB [30], INRIA [10], ETH [13], and TUDBrussels [41]. All of the aforementioned datasets were typically collected for surveillance application. None of these datasets…”
MethodFranke, U., Pfeiffer, D., Rabe, C., Knoeppel, C., Enzweiler, M., Stein, F., & Herrtwich, R. G. (2013) · 2013 IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.36 · Cited by 145
“a variant of [27].”
Pedestrian Models for Autonomous Driving Part II: High-Level Models of Human Behavior
Camara, F., Bellotto, N., Coşar, S., Weber, F., Nathanael, D., Althoff, M., Wu, J., Ruenz, J., Dietrich, A., Markkula, G. M., et al. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3006767 · Cited by 187
A Multilevel Mixture-of-Experts Framework for Pedestrian Classification
Enzweiler, M., & Gavrila, D. M. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2142006 · Cited by 150
Multi-stage Contextual Deep Learning for Pedestrian Detection
Zeng, X., Ouyang, W., & Wang, X. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.22 · Cited by 149
“The experiments are conducted on three public datasets, the Caltech dataset [14], the ETHZ dataset [20] and the TUD-Brussels dataset [54].”
MethodA Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook
Liu, M., Yurtsever, E., Fossaert, J., Zhou, X., Zimmer, W. M. X., Cui, Y., Žagar, B. L., & Knoll, A. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3394735 · Cited by 216
Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
Agarwal, S., du Terrail, J. O., & Jurie, F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.03193 · Cited by 107
“TUD-Brussels [Wojek et al., 2009] is from the TU Darmstadt University and contains image pairs recorded in a crowded urban setting with an on-board camera from a car.”
BackgroundSingle-Pedestrian Detection Aided by Multi-pedestrian Detection
Ouyang, W., & Wang, X. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.411 · Cited by 144
“The proposed framework is evaluated on three public datasets: Caltech [10], TUD-Brussels [36] and ETH [12].”
MethodInfluentialScene-Specific Pedestrian Detection for Static Video Surveillance
Wang, X., Wang, M., & Li, W. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.124 · Cited by 144
“[7], [8], [9], [10], [11], [12], [13], [14], [15], [16], [17], [18], [19],”
Domain Adaptation of Deformable Part-Based Models
Xu, J., Ramos, S., Vazquez, D., & Lopez, A. M. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2327973 · Cited by 135
Learning scene-specific pedestrian detectors without real data
Hattori, H., Boddeti, V. N., Kitani, K., & Kanade, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299006 · Cited by 127
“This stands in contrast to the large body of work focused primarily on pedestrian detection from a mobile platform [12, 13, 41, 11].”
ResultObject Detection in Adverse Weather for Autonomous Driving through Data Merging and YOLOv8
Kumar, D., & Muhammad, N. (2023) · Sensors · doi:10.3390/s23208471 · Cited by 156
“Daimler Arban Segmentation [28], Leuven [29], TUDBrus-sels [30], ETH [31], INRIA [32], Daimler-DB [33], NICTA [34], CVC [35], Daimler-CB [36], Caltech [37], Camvid [38], and many more notable datasets have contributed to the diversity and quantity of resources.”
BackgroundPedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning
Paisitkriangkrai, S., Shen, C., & Hengel, A. V. D. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2474388 · Cited by 130
PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes
Chi, C., Zhang, S., Xing, J., Lei, Z., Li, S. Z., & Zou, X. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6690 · Cited by 134
Learning Multilayer Channel Features for Pedestrian Detection
Cao, J., Pang, Y., & Li, X. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2694224 · Cited by 121
“4) Experiments on Caltech dataset [11], INRIA dataset [8], ETH dataset [13], TUD-Brussels dataset [49], and”
MethodInfluentialVision based victim detection from unmanned aerial vehicles
Andriluka, M., Schnitzspan, P., Meyer, J., Kohlbrecher, S., Petersen, K., von Stryk, O., Roth, S., & Schiele, B. (2010) · 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2010.5649223 · Cited by 110
“Models of this type have recently been extended to incorporate motion [10], [36] and color [35] features.”
MethodSelf-citationObject class detection: A survey
Zhang, X., Yang, Y.-H., Han, Z., Wang, H., & Gao, C. (2013) · ACM Computing Surveys · doi:10.1145/2522968.2522978 · Cited by 107
“2006], and improved the performance of onboard pedestrian detection [Wojek et al. 2009].”
BackgroundMethodTen Years of Pedestrian Detection, What Have We Learned?Preprint
Benenson, R., Omran, M., Hosang, J., & Schiele, B. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1411.4304 · Cited by 141
“Multiple public pedestrian datasets have been collected over the years; INRIA [1], ETH [2], TUD-Brussels [3], Daimler [4] (Daimler stereo [5]), Caltech-USA [6], and KITTI [7] are the most commonly used ones.”
BackgroundSelf-citationROAD: The Road Event Awareness Dataset for Autonomous Driving
Singh, G., Akrigg, S., Maio, M. D., Fontana, V., Alitappeh, R. J., Khan, S., Saha, S., Jeddisaravi, K., Yousefi, F., Culley, J., et al. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3150906 · Cited by 143
“Other datasets only provide pedestrian detection annotation [29], [30], [31], [32], [33], [34], [35].”
BackgroundNightOwls: A Pedestrians at Night Dataset
Neumann, L., Karg, M. E., Zhang, S., Scharfenberger, C., Piegert, E., Mistr, S., Prokofyeva, O., Thiel, R., Vedaldi, A., Zisserman, A., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20887-5_43 · Cited by 125
“85 TUD [17] 508 1k 0 145 - - - - - - - - 508 2.”
Self-citationPANDA: A Gigapixel-Level Human-Centric Video Dataset
Wang, X., Zhang, X., Zhu, Y., Guo, Y., Yuan, X., Xiang, L., Wang, Z., Ding, G., Brady, D. J., Dai, Q., et al. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00333 · Cited by 143
Video Event Detection: From Subvolume Localization to Spatiotemporal Path Search
Tran, D., Yuan, J., & Forsyth, D. A. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.137 · Cited by 104
“These features are then trained on a linear support vector machine (SVM) with one more additional bootstrapping round on hard negative set of TUD-MotionPairs.”
MethodInfluentialPedestrian and Cyclist Detection and Intent Estimation for Autonomous Vehicles: A Survey
Ahmed, S., Huda, M. N., Rajbhandari, S., Saha, C., Elshaw, M., & Kanarachos, S. A. (2019) · Applied Sciences · doi:10.3390/app9112335 · Cited by 112
“Pedestrian Caltech [173] KITTI [176] CityScapes [177] KAIST [106] Daimler [178] ETH [69] TUD-Brussels [175] PASCAL-VOC [179]”
BackgroundMethodComprehensive review of recent developments in visual object detection based on deep learning
Edozie, E., Shuaibu, A. N., John, U. K., & Sadiq, B. O. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11284-w · Cited by 118
Prioletti, A., Møgelmose, A., Grisleri, P., Trivedi, M. M., Broggi, A., & Moeslund, T. B. (2013) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2013.2262045 · Cited by 103
Person Re-identification Meets Image SearchPreprint
Zheng, L., Shen, L., Tian, L., Wang, S., Bu, J., & Tian, Q. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.02171 · Cited by 93
“For other datasets, the codebook is trained on the independent TUD-Brussels dataset [37].”
MethodKohli, P., & Chadha, A. (2020) · Lecture Notes in Networks and Systems · doi:10.1007/978-3-030-12388-8_19 · Cited by 75
“ion datasets have been made publicly available over the years. ETH [50], INRIA [12], Caltech-USA [30, 51] , KITTI [52], and TUD-Brussels 2 Figure 2. (Frame 75 after applying Gamma correction ( = 3:5) [53] are a few of the more popular of them. Different datasets vary in the environmental settings (urban, city, mountai…”
Pedestrian detection with a Large-Field-Of-View deep network
Angelova, A., Krizhevsky, A., & Vanhoucke, V. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139256 · Cited by 107
“Pedestrian detection has been a topic of many recent works, many of which have had significant impact [22], [5], [23], [6], [24], [7], [8], [25], [9].”
BackgroundThe Benefits of Dense Stereo for Pedestrian Detection
Keller, C. G., Enzweiler, M., Rohrbach, M., Llorca, D. F., Schnörr, C., & Gavrila, D. M. (2011) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2011.2143410 · Cited by 102
“In terms of discriminative models, support vector machines (SVMs) are widely used in both linear [5], [8], [46], [49], [51] and nonlinear variants [28], [35].”
InfluentialDetection of Sudden Pedestrian Crossings for Driving Assistance Systems
Xu, Y., Xu, D., Lin, S., Han, T. X., Cao, X., & Li, X. (2011) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2011.2175726 · Cited by 98
“7(a), one can draw the following conclusion: 1) the Haar-like+Adaboost method has the lowest performance; this observation is consistent with previous studies [6], [7], which indicates that the HOG feature has more discriminative power for larger sized pedestrian detection; 2) NMS increases the accuracy of HOG classif…”
BackgroundMethodResultMonocular Visual Scene Understanding: Understanding Multi-Object Traffic Scenes
Wojek, C., Walk, S., Roth, S., Schindler, K., & Schiele, B. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.174 · Cited by 97
“The DPM detector and the six partial HOG detectors that are used in combination with DPM are trained on the INRIA Person dataset [55], while the motion enhanced detectors are trained on TUDMotionPairs [57].”
MethodSelf-citationThe adaptability and challenges of autonomous vehicles to pedestrians in urban China
Wang, K., Li, G., Chen, J., Yan, L., Chen, T., Chen, L., & Xia, Q. (2020) · Accident Analysis & Prevention · doi:10.1016/j.aap.2020.105692 · Cited by 90
“, 2007) 12,000 NO RFPPI (RPN+BF, 30%) 2007 TUDBrussels(Wojek et al., 2009) 3247 NO P-R (SpatialPooling,47%) 2009”
Zhu, S., & Meng, Q. (2022) · Accident Analysis & Prevention · doi:10.1016/j.aap.2022.106769 · Cited by 92
Too Far to See? Not Really!—Pedestrian Detection With Scale-Aware Localization Policy
Zhang, X., Cheng, L., Li, B. H., & Hu, H. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2818018 · Cited by 87
“For benchmarks, three widely used datasets are considered in our experiments, namely Caltech [11], ETH [9] and TUD-Brussels [43].”
MethodAutomatic Vacant Parking Places Management System Using Multicamera Vehicle Detection
Martín-Nieto, R., García‐Martín, Á., Hauptmann, A. G., & Martínez, J. M. (2018) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2018.2838128 · Cited by 90
“measured in terms of Precision-Recall (PR) curves [34]–[36].”
BackgroundA new benchmark for stereo-based pedestrian detection
Keller, C. G., Enzweiler, M., & Gavrila, D. M. (2011) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2011.5940480 · Cited by 95
“Detection datasets, e.g. [1], [5], [7], [9], [12], [22], [23], [24], containing cut-outs for training and full images for test data are used to benchmark integrated pedestrian detection systems.”
MethodMonocular 3D scene understanding with explicit occlusion reasoning
Wojek, C., Walk, S., Roth, S., & Schiele, B. (2011) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2011.5995547 · Cited by 92
“The SVM for three of the detectors is trained on the upper, left and right halves of the block grids (rounded up).”
MethodSelf-citationReview on computer vision techniques in emergency situations
Lopez-Fuentes, L., van de Weijer, J., González-Hidalgo, M., Skinnemoen, H., & Bagdanov, A. D. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5276-7 · Cited by 90
“…studied in this survey, HOG was used to detect persons in disaster areas [7,141,142], to detect pedestrians for on board vehicle cameras [144,165] but also to characterize other objects such as flames, smoke and traffic signs [8, 160,179] and as a descriptor for a tracking algorithm [51] in…”
Early Detection of Sudden Pedestrian Crossing for Safe Driving During Summer Nights
Jeong, M., Ko, B. C., & Nam, J.-Y. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2539684 · Cited by 78
“In recent years, there have been a number of data sets developed for pedestrian detection in video sequences, such as ETH [31], TUD-Brussels [32], Daimler [33], and the Caltech Pedestrian [34] data sets.”
BackgroundPedestrian Detection for UAVs Using Cascade Classifiers with Meanshift
Aguilar, W. G., Luna, M. A., Moya, J. F., Abad, V., Parra, H., & Ruiz, H. (2017) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icsc.2017.83 · Cited by 78
“Other pedestrian datasets include: Caltech Pedestrian Dataset [24], KITTI[25], MIT[26], NICTA[27], ETH [28], TUD-Brussels [29], Dalmier (DB) [30], and others.”
MethodMonocular 3D Scene Modeling and Inference: Understanding Multi-Object Traffic Scenes
Wojek, C., Roth, S., Schindler, K., & Schiele, B. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15561-1_34 · Cited by 80
“2% over the detector used in our system [20].”
MethodSelf-citationReal-time pedestrian detection with deformable part models
Cho, H., Rybski, P. E., Bar-Hillel, A., & Zhang, W. (2012) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2012.6232264 · Cited by 75
“In the past few years, impressive progress has been made, such as found the works of [17], [19], [4], [11], [24], [6], and these insights suggest that they can and should be applied to real world applications.”
BackgroundDaniilidis, K., Paragios, N., & Maragos, P. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15567-3 · Cited by 70
“The same features and classifiers were used recently in [4].”
BackgroundMethodInfluentialEvaluation and Acceleration of High-Throughput Fixed-Point Object Detection on FPGAs
Ma, X., Najjar, W. A., & Roy–Chowdhury, A. K. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2360030 · Cited by 77
“We have used four benchmarks to evaluate our fixedpoint HOG detection: Daimler Mono Pedestrian Detection [27], TUD-Brussels [26], Caltech Pedestrian Detection [28], and three sequences from ETH datasets (the BAHNHOF, JELMOLI, and SUNNY DAY sequences) [29].”
MethodPedestrian detection with super-resolution reconstruction for low-quality image
Jin, Y., Zhang, Y., Cen, Y., Li, Y., Mladenovic, V. M., & Voronin, V. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.107846 · Cited by 71
Human Detection by Quadratic Classification on Subspace of Extended Histogram of Gradients
Satpathy, A., Jiang, X., & Eng, H. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2264677 · Cited by 69
“…for human detection usually use classifiers such as Support Vector Machines (SVM) [3], [8]–[10], [22], [25], [29], [30], [33]–[37], [48], [50], [59] and cascade-structured boosting-based classifiers [4]–[7], [11], [13], [14], [16], [24], [26], [27], [32], [38], [44]–[47], [49], [51],…”
BackgroundMultispectral pedestrian detection based on deep convolutional neural networks
Hou, Y.-L., Song, Y., Hao, X., Shen, Y., Qian, M., & Chen, H. (2018) · Infrared Physics & Technology · doi:10.1016/j.infrared.2018.08.029 · Cited by 70
Partial Occlusion Handling in Pedestrian Detection With a Deep Model
Ouyang, W., Zeng, X., & Wang, X. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2501940 · Cited by 65
“Since a lot of occluded pedestrians in the datasets like INRIA, ETHZ, and TUD-Brussels are not considered as positive testing samples, the occluded pedestrians are relabeled in our dataset.”
MethodBenchmarking a large-scale FIR dataset for on-road pedestrian detection
Xu, Z., Zhuang, J., Liu, Q., Zhou, J., & Peng, S. (2018) · Infrared Physics & Technology · doi:10.1016/j.infrared.2018.11.007 · Cited by 63
“Several visible spectrum pedestrian datasets have been proposed including INRIA [14], ETH [15], TudBrussels [16], and Daimler [17].”
MethodWalambe, R. A., Marathe, A., Kotecha, K. V., & Ghinea, G. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/5278820 · Cited by 66
“…datasets for these models is of equal importance, and over time several datasets have been introduced, including INRIA [15], ETH [16], TUD-Brussels [17], and KITTI [18]. datasets have been used for several autonomous vehicle-specific tasks, including 2D object detection, 3D object detection,…”
MethodOcclusion Handling and Multi-Scale Pedestrian Detection Based on Deep Learning: A Review
Li, F., Li, X., Liu, Q., & Li, Z. (2022) · IEEE Access · doi:10.1109/access.2022.3150988 · Cited by 62
“In contrast to the generic object detection datasets, some datasets specially used for pedestrian detection have been collected over the years, such as MIT [124] INRIA [13], ETH [44], USC [125], [126], TUD-Brussels [127], and Daimler [27].”
STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes
Cong, P., Zhu, X., Qiao, F., Ren, Y., Peng, X., Hou, Y., Xu, L., Yang, R., Manocha, D., & Ma, Y. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01899 · Cited by 74
“Early datasets, like INRIA [15], ETH [18], TUD-Brussels [44], and Daimler [17] are too small for the training and generalization of deep learning-based methods.”
BackgroundPedestrian Detection Using Multi-Scale Structure-Enhanced Super-Resolution
Hsu, W., & Yang, P.-Y. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3287574 · Cited by 60
“This dataset includes pedestrian occluded images in Caltech [35], ETH [31], TUD-Brussels [36], INRIA [28], and Caviar’s datasets, and images collected by the Chinese University of Hong Kong, amounting to a total of 1063 images.”
MethodTask-Driven Semantic Coding via Reinforcement Learning
Li, X., Shi, J., & Chen, Z. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3091909 · Cited by 56
Optimal spatio-temporal path discovery for video event detection
Tran, D., & Yuan, J. (2011) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2011.5995416 · Cited by 55
“Datasets: we use two datasets, TUD-MotionPairs [21] for training and our YouTube Walking for testing.”
MethodSingle-Pedestrian Detection Aided by Two-Pedestrian Detection
Ouyang, W., Zeng, X., & Wang, X. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2377734 · Cited by 55
A Review of the Impact of Rain on Camera-Based Perception in Automated Driving Systems
Brophy, T., Mullins, D., Parsi, A., Horgan, J., Ward, E., Denny, P., Eising, C., Deegan, B. M., Glavin, M., & Jones, E. (2023) · IEEE Access · doi:10.1109/access.2023.3290143 · Cited by 60
Pedestrian Detection via Body Part Semantic and Contextual Information With DNN
Wang, S., Cheng, J., Liu, H., Feng, W., & Zhou, H. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2829602 · Cited by 54
“However, it used extra datasets ETH [54] and TudBrussels [55] for training.”
MethodGawande, U. H., Hajari, K. O., & Golhar, Y. (2020) · IntechOpen eBooks · doi:10.5772/intechopen.90810 · Cited by 58
Metadata
- Authors
- Wojek, C., Walk, S., & Schiele, B.
- Affiliations
- Technische Universität Darmstadt (DE)
- ORCID
- Schiele, Bernt
- Venue
- 2009 IEEE Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2009-06
- Pages
- 794-801
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2127420331
- Cited by
- 350
- References
- 37
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 1 · 2023: 8 · 2022: 13 · 2021: 21 · 2020: 24 · 2019: 25 · 2018: 27 · 2017: 30 · 2016: 24 · 2015: 30 · 2014: 29 · 2013: 37 · 2012: 19
- FWCI
- 20.14
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- Max Planck Digital Library (submittedVersion)
- MPG.PuRe (Max Planck Society) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- pedestrian detection, onboard camera, motion information, multi-cue fusion, feature combination, sliding window, classifier comparison, urban driving
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.