On the Performance of One-Stage and Two-Stage Object Detectors in Autonomous Vehicles Using Camera Data
Open accessThe DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
Abstract
Object detection using remote sensing data is a key task of the perception systems of self-driving vehicles. While many generic deep learning architectures have been proposed for this problem, there is little guidance on their suitability when using them in a particular scenario such as autonomous driving. In this work, we aim to assess the performance of existing 2D detection systems on a multi-class problem (vehicles, pedestrians, and cyclists) with images obtained from the on-board camera sensors of a car. We evaluate several one-stage (RetinaNet, FCOS, and YOLOv3) and two-stage (Faster R-CNN) deep learning meta-architectures under different image resolutions and feature extractors (ResNet, ResNeXt, Res2Net, DarkNet, and MobileNet). These models are trained using transfer learning and compared in terms of both precision and efficiency, with special attention to the real-time requirements of this context. For the experimental study, we use the Waymo Open Dataset, which is the largest existing benchmark. Despite the rising popularity of one-stage detectors, our findings show that two-stage detectors still provide the most robust performance. Faster R-CNN models outperform one-stage detectors in accuracy, being also more reliable in the detection of minority classes. Faster R-CNN Res2Net-101 achieves the best speed/accuracy tradeoff but needs lower resolution images to reach real-time speed. Furthermore, the anchor-free FCOS detector is a slightly faster alternative to RetinaNet, with similar precision and lower memory usage.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures






Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“The Deep Residual Networks (ResNet) [20] succeeded in addressing complex image problems achieving the best results in competitions such as ILSVRC [39] and COCO [13].”
BackgroundMethodVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“Faster R-CNN uses a convolutional backbone network, such as VGG [19] or ResNet [20], which outputs global feature maps.”
MethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 2×
“ResNet, ResNeXt, and Res2Net The Deep Residual Networks (ResNet) [20] succeeded in addressing complex image problems achieving the best results in competitions such as ILSVRC [39] and COCO [13].”
BackgroundRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
(2016) · Cited by 31,590
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939 · cited 1×
“For instance, feature pyramid networks (FPN) were proposed in order to crop RoI features from different levels depending on the scale [21].”
BackgroundMobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755
Cited by
Items 101–200 of 269
Meivel, S., Devi, K. I., Subramanian, A. S., & Kalaiarasi, G. (2024) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-024-01963-6 · Cited by 7
Anchor-Free Object Detection with Scale-Aware Networks for Autonomous Driving
Piao, Z., Wang, J., Tang, L., Zhao, B., & Zhou, S. (2022) · Electronics · doi:10.3390/electronics11203303 · Cited by 7
Automatic Team Assignment and Jersey Number Recognition in Football Videos
Alhejaily, R., Alhejaily, R., Almdahrsh, M., Alessa, S., & Albelwi, S. A. (2023) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2023.033062 · Cited by 8
Using Computer Vision to Collect Information on Cycling and Hiking Trails Users
Miguel, J., Mendonça, P., Quelhas, A., Caldeira, J. M. L. P., & Soares, V. N. G. J. (2024) · Future Internet · doi:10.3390/fi16030104 · Cited by 8
Patel, S. (2023) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2023.0140379 · Cited by 8
“One-stage object detection models, also known as single-shot detectors, are designed to detect objects in a single pass over an input image [18].”
BackgroundChowdhury, R. I., Anjom, J., & Hossain, M. I. A. (2024) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2024.102191 · Cited by 9
A Two-Stage YOLOv8 Approach for Waste Detection and Classification in Cognitive Cities
Nayfeh, A., Al-Azani, S., & Samma, H. (2025) · Transportation research procedia · doi:10.1016/j.trpro.2025.03.111 · Cited by 7
Shad, I., Zhang, Z., Asim, M., Al‐Habib, M. I., Chelloug, S. A., & El‐Latif, A. A. A. (2025) · Journal of Radiation Research and Applied Sciences · doi:10.1016/j.jrras.2025.101534 · Cited by 13
Artificial intelligence-based model for efficient object detection in autonomous vehicles
Zhang, Z., Zhang, Q., Liu, H., Gao, Y., & Wang, L. (2025) · Journal of Intelligent Transportation Systems · doi:10.1080/15472450.2025.2499591 · Cited by 5
Tennis Ball Collection Robot Based on MobileNet-SSD
Zhu, Z., Gao, Y., & Gu, S. (2021) · International Conference on Intelligent Control and Information Processing · doi:10.1109/icicip53388.2021.9642172 · Cited by 5
Deep Learning for Arbitrary-Shaped Water Pooling Region Detection on Aerial Images
Mylvaganam, P., & Dissanayake, M. B. (2022) · Moratuwa Engineering Research Conference (MERCon) · doi:10.1109/mercon55799.2022.9906204 · Cited by 5
“The main difference between these two categories is that the two-stage detector gives better results with high localization and overall accuracy, whereas the one-stage algorithm predicts the results at high speed [17].”
BackgroundCar Classification Based on Image Using Transfer Learning Convolutional Neural Network
Saputra, W. S. J., Puspaningrum, E. Y., Syahputra, W. F., Sari, A. P., Via, Y. V., & Idhom, M. (2022) · IEEE Information Technology International Seminar (ITIS) · doi:10.1109/itis57155.2022.10010073 · Cited by 5
“The faster R-CNN Res2Net-101 achieves the best speed/accuracy tradeoff but requires lower resolution images to achieve real-time speeds [13].”
BackgroundPavement Crack Detection from UAV Images Using YOLOv4
Mahmud, M. N., Sabri, N. N. N. A., Osman, M. K., Ismail, A. P., Ahmad, F., Idris, M., Sulaiman, S. N., Saad, Z., Ibrahim, A., & Rabiain, A. H. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-43520-1_7 · Cited by 5
Sperling, N., & Ernst, R. (2024) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2024-spring62846.2024.10683426 · Cited by 6
“The authors in [14] have found that object detectors with sufficient accuracy require more than 100 ms to process high resolution input images (1280 × 1920) and even scaled down images (640 × 960) still require at least 60 ms to compute.”
BackgroundArrahmah, A. I., Rahmania, R., & Saputra, D. E. (2022) · Bulletin of Electrical Engineering and Informatics · doi:10.11591/eei.v11i4.3784 · Cited by 5
NAM-YOLOV7: An Improved YOLOv7 Based on Attention Model for Animal Death Detection
Sirisha, U., Chandana, B. S., & Harikiran, J. (2023) · Traitement du signal · doi:10.18280/ts.400239 · Cited by 8
A Lightweight and Enhanced YOLO11-Based Method for Small Object Surface Defect DetectionPreprint
Rao, H., Zhan, H., Wang, R., & Yu, J. (2025) · Research Square · doi:10.21203/rs.3.rs-6093937/v1 · Cited by 5
Real‐Time Tool Detection in Laparoscopic Datasets for Surgical Training in Low‐Resource Settings
Choudhry, O., Ali, S., Biyani, C. S., & Jones, D. A. (2025) · Healthcare Technology Letters · doi:10.1049/htl2.70045 · Cited by 6
Patel, M. K., Bull, G., Egan, L. M., Swain, N., Rolland, V., Stiller, W. N., & Conaty, W. C. (2026) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2025.104379 · Cited by 5
Rosa, G. J. M., Afonso, J. M. S., Gaspar, P. D., Soares, V. N. G. J., & Caldeira, J. M. L. P. (2024) · Information · doi:10.3390/info15030169 · Cited by 6
Van, D. D., Le, V.-H., Do, H.-S., Phan, V.-N., & Te, T.-H. (2024) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v34.i3.pp1603-1617 · Cited by 4
“CNNs to solve the object classification/recognition problem of computer vision are divided into two types [18]: one-stage CNNs YOLO series/family [19], SSD series/family [20]) and two-stage CNNs.”
Orgeira-Crespo, P., Gabín-Sánchez, C., Agelet, F. A., & Rey, G. (2024) · Applied Sciences · doi:10.3390/app14125113 · Cited by 4
An enhanced machine vision system for smart poultry farms using deep learning
Natho, P., Boonying, S., Bonguleaum, P., Tantidontanet, N., & Chamuthai, L. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101083 · Cited by 4
Using Perception Cues for Context-Aware Navigation in Dynamic Outdoor Environments
Wigness, M., Rogers, J. G., Tsai, C.-E., Mertz, C., Navarro‐Serment, L. E., & Oh, J. (2021) · Field Robotics · doi:10.55417/fr.2021001 · Cited by 4
“A more specific analysis was performed, focusing on object detection for autonomous vehicles in urban environments (Carranza-García et al., 2020).”
MethodHuang, Q., Yang, K., Zhu, Y., Chen, L., & Cao, L. (2023) · Electronics · doi:10.3390/electronics12224589 · Cited by 4
ADVANCED WILD ANIMAL DETECTION AND ALERT SYSTEM USING THE YOLO V5 MODEL POWERED BY AI
NAGAGOPIRAJU, V., PINNINTI, S., TAMMA, A., KAJJAYAM, S. T., & KAKARLA, K. (2024) · Türk bilgisayar ve matematik eğitimi dergisi · doi:10.61841/turcomat.v15i1.14556 · Cited by 4
A Study on the Performance Improvement of a Conical Bucket Detection Algorithm Based on YOLOv8s
Li, X., Li, G., & Zhang, Z. (2024) · World Electric Vehicle Journal · doi:10.3390/wevj15060238 · Cited by 6
Smith, E. S., Fleet, C., KING, S. E., Mackaness, W., Walker, H., & Scott, C. E. (2024) · Computers Environment and Urban Systems · doi:10.1016/j.compenvurbsys.2024.102219 · Cited by 6
YOLO-Based Detector for Enhancing Workplace Safety: Real-Time PPE Detection and Monitoring
Amri, S., Ouannes, L., Sahbani, A., & Amara, N. E. B. (2024) · IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa63423.2024.10912638 · Cited by 4
“Keypoint-based methods like CornerNet and ExtremeNet [16] locate key points for bounding box generation but are slower due to complex post-processing [16].”
InfluentialCGI-Based Synthetic Data Generation and Detection Pipeline for Small Objects in Aerial Imagery
Patel, R., Chandalia, D., Nayak, A., Jeyabose, A., & Jijo, D. (2025) · IEEE Access · doi:10.1109/access.2025.3553530 · Cited by 5
“Modernobject detection algorithms are broadly categorized into one-stage and two-stage processes [25].”
An Automatic Defect Detection System for Synthetic Shuttlecocks Using Transformer Model
Lin, C.-S., & Hsieh, H.-Y. (2022) · IEEE Access · doi:10.1109/access.2022.3165224 · Cited by 5
“Recently, deep learning based approaches have become the most popular solution in this research field and can be divided into one-stage detector and two-stage detector [9].”
BackgroundPersonal Protective Equipment use inspection, real time surveillance with YOLO
Huanca, G., Ordoñez, J., & Menacho, C. (2022) · International Conference on Machine Learning Technologies (ICMLT) · doi:10.1145/3529399.3529512 · Cited by 4
“In 2018, YOLO v3 was proposed by J. Redmon and A. Farhadi [9] to improve the detection accuracy, this was achieved including multi-scale predictions and a backbone as DarkNet-53, which use residual blocks and hop connections [8].”
BackgroundMethodInfluentialMendes, F., Fernandes, A. M., Fernandes, L., Piedade, F., & Chaves, P. (2022) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet55527.2022.9872921 · Cited by 4
Computer vision-based human-machine collision warning system on construction site
Gu, B., Guo, H., Huang, Y., Lim, H. W., & Fang, D. (2022) · IOP Conference Series Earth and Environmental Science · doi:10.1088/1755-1315/1101/3/032014 · Cited by 4
AI-based Maize and Weeds detection on the edge with CornWeed Dataset
Iqbal, N., Manss, C., Scholz, C., Koenig, D., Igelbrink, M., & Ruckelshausen, A. (2023) · Annals of Computer Science and Information Systems · doi:10.15439/2023f2125 · Cited by 7
Real-Time SLAM and Faster Object Detection on a Wheeled Lifting Robot with Mobile-ROS Interaction
Lei, X., Chen, Y., & Zhang, L. (2024) · Applied Sciences · doi:10.3390/app14145982 · Cited by 3
Deep learning for extraneous material detection in a rice processing factory
Chuang, P., Cheng, M.-H., Chi, C.-H., & Ku, H. (2025) · Food Control · doi:10.1016/j.foodcont.2025.111804 · Cited by 6
Hybrid YOLOv5s-faster R-CNN detector for complex road-scene object detection
Byenkya, N. L., Rose, N., & Taremwa, D. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01253-9 · Cited by 3
“Despite this promise, many existing hybrid approaches either rely on computationally expensive region proposal networks or lack principled fusion strategies, resulting in limited gains or excessive overhead [11].”
Real-Time 3D Bounding Box Estimation with RCNN-Resnet101 and Adaptive Projection Matrices
Kumar, U., Parihar, P., Vaithiyanathan, D., & Muniraj, M. (2024) · International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT) · doi:10.1109/icaect60202.2024.10468965 · Cited by 3
“This pre-trained model operates as a robust feature extractor, harnessing its learned representations to identify and locate objects within 2D image frames [17-19].”
BackgroundVerma, R., Vishwakarma, S. K., & Bodade, R. M. (2024) · IETE Journal of Research · doi:10.1080/03772063.2024.2357619 · Cited by 3
“Solving the problem of object detection can be approached through various methods, and models can be categorized into three distinct groups [2]: (cid:129) Two-stage detectors: These models consist of two stages, incorporating both a region-proposal network and a detection network.”
An Efficient Approach to Detecting Lung Nodules Using Swin Transformer
Shakuri, S., & Rezvanian, A. (2024) · Iranian Conference on Intelligent Systems (ICIS) · doi:10.1109/icis64839.2024.10887472 · Cited by 3
Le, V.-H. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-20743-z · Cited by 3
Application Based Cigarette Detection on Social Media Platforms Using Machine Learning Algorithms
Hashmi, M. U., Nguyen, N. D., Johnstone, M., Backholer, K., & Bhatti, A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-91387-8_5 · Cited by 3
Development of a Technique for Classifying Photovoltaic Panels Using Sentinel-1 and Machine Learning
Lee, S.-H., Yoon, D., Lee, S.-K., Oh, K.-Y., & Lee, M.-J. (2022) · Journal of Sensors · doi:10.1155/2022/1121971 · Cited by 3
Deep Network-based Slow Feature Analysis for Human Fall Detection
Pramanik, A., Venkatagiri, K., Sarkar, S., & Pal, S. K. (2022) · International Conference on Computational Modelling, Simulation and Optimization (ICCMSO) · doi:10.1109/iccmso58359.2022.00024 · Cited by 5
“There are two types of object detectors, such as twostage and one-stage [5].”
BackgroundГридин, В. Н., Novikov, I. A., Салем, Б. Р., & Солодовников, В. И. (2023) · International Conference on Information Technology and Nanotechnology (ITNT) · doi:10.1109/itnt57377.2023.10139188 · Cited by 4
“Within the framework of object detection models, two main concepts of architectures[9] are distinguished: OneStage Detector and Two-Stage Detector.”
MethodAIDCON: An Aerial Image Dataset and Benchmark for Construction Machinery
Ersöz, A. B., Pekcan, O., & Akbaş, E. (2024) · Remote Sensing · doi:10.3390/rs16173295 · Cited by 3
Object Detection for Autonomous Vehicle using Single Camera with YOLOv4 and Mapping Algorithm
Sahal, M., Kurniawan, A. O., & Kadir, R. E. A. (2021) · International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · doi:10.1109/isriti54043.2021.9702764 · Cited by 4
Based on improved YOLOv8 and Bot SORT surveillance video traffic statisticsPreprint
Yang, Y., Pi, D., Wang, L., Bao, M., Ge, J., Yuan, T., Yu, H., & Zhou, Q. (2024) · Research Square · doi:10.21203/rs.3.rs-4161504/v1 · Cited by 3
Perera, I. J. J. U. N., Sandaruwan, R. D. C., & Bellanthudawa, B. K. A. (2025) · Wiley eBooks · doi:10.1002/9781394237029.ch17 · Cited by 5
Ilamathi, M., Ramakrishnan, S., & Babusankar, R. K. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105081 · Cited by 3
The Development of a Prototype Solution for Collecting Information on Cycling and Hiking Trail Users
Miguel, J., Mendonça, P., Quelhas, A., Caldeira, J. M. L. P., & Soares, V. N. G. J. (2024) · Information · doi:10.3390/info15070389 · Cited by 3
Exploring deep learning strategies for intervertebral disc herniation detection on veterinary MRI
Huang, S., Deng, G., Kang, Y., Li, J., Li, J., & Lyu, M. (2024) · Scientific Reports · doi:10.1038/s41598-024-67749-5 · Cited by 3
“methods can fully replace two-stage methods, especially in specialized areas 23,24 .”
MethodSorrilha-Rodrigues, A. G., Paes, J. L. A. R., Rizk, Y. S., da Silva, F., Rosalem, R. F., de Arruda, C. C. P., & Carollo, C. A. (2024) · ACS Omega · doi:10.1021/acsomega.4c08735 · Cited by 2
Aishwarya, K. V., Asuntha, A., & Murugan, J. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-20752-y · Cited by 2
“1 and 2 [39].”
UPAQ: A Framework for Real-Time and Energy-Efficient 3D Object Detection in Autonomous Vehicles
Balasubramaniam, A., Sunny, F., & Pasricha, S. (2025) · Design, Automation, and Test in Europe · doi:10.23919/date64628.2025.10993184 · Cited by 2
Computer vision-based safe distance-estimation method to prevent forklift tip-overs
Sabir, A., Hussain, R., Abbas, M. S., Zaidi, S. F. A., Yang, J., & Park, C. (2025) · International Journal of Occupational Safety and Ergonomics · doi:10.1080/10803548.2025.2543150 · Cited by 2
Du, J., Gao, R., Wang, Y., Zhao, J., Meng, Y., & Shao, W. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114462 · Cited by 2
An explainable deep learning model for dental caries detection and segmentation
Brahmi, W., Jdey, I., & Drira, F. (2026) · The Visual Computer · doi:10.1007/s00371-026-04540-9 · Cited by 2
Towards automatic placement of media objects in a personalised TV experience
Allan, B., Kegel, I., Kalidass, S. H., Kharechko, A., Milliken, M., McClean, S. I., Scotney, B. W., & Zhang, S. (2022) · Multimedia Systems · doi:10.1007/s00530-022-00974-y · Cited by 2
“Research conducted in 2021 by the University of Sevilla on real-time single-stage and two-stage detectors [14] illustrates similar findings, i.e., the single-stage detectors such as FCOS and YOLOv3 outperform two-stage detectors such as Faster R-CNN in inference timing (per second).”
BackgroundMethodRajasekaran, S. B. (2023) · Electric Power Components and Systems · doi:10.1080/15325008.2023.2203713 · Cited by 2
DETECTION AND RECOGNITION OF ROAD SIGNS USING YOLOv5
Haitam, E., Rafalia, N., & Abouchabaka, J. (2023) · Proceedings on Engineering Sciences · doi:10.24874/pes05.03.017 · Cited by 3
“The biggest drawback of two-stage architectures is that they do not excel at performing real-time detection and require multiple GPUs to train the model as shown by Carranza-García et al. (2020), thus, the YOLO model has been proposed to address these limitations.”
MethodSarath, P. (2023) · International Conference on Electronics, Communication and Aerospace Technology (ICECA) · doi:10.1109/iceca58529.2023.10395664 · Cited by 2
“…as minimize the consumption time thus, the contributions is as follows, Golden Levy optimization: GLO is developed by integrating the typicalcharacteristics such as Levy of both Golden eagle optimization [9] as well as the bald eagle optimization algorithm [6] by arithmetically and theoretically.”
BackgroundMethodDental caries detection using faster region-based convolutional neural network with residual network
Lanyak, A. C. F., Prasetiadi, A., Widodo, H. B., Ghani, M. H., & Athallah, A. (2024) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v13.i2.pp2027-2035 · Cited by 5
“The former involves separating the detection process into a region proposal module and a classification module, while the latter integrates the detection into a single feed-forward fully convolutional network that directly provides the bounding boxes and object classification [15].”
Kolekar, S., Gite, S., Pradhan, B., & Alamri, A. (2024) · International Journal on Smart Sensing and Intelligent Systems · doi:10.2478/ijssis-2024-0025 · Cited by 3
Islam, F., Nabi, M. M., Ball, J. E., & Goodin, C. T. (2024) · IEEE Access · doi:10.1109/access.2024.3457685 · Cited by 3
Alkhonaini, M. A., Mengash, H. A., Nemri, N., Ebad, S. A., Alotaibi, F. A., Aljabri, J., AlZahrani, Y., & Alnfiai, M. M. (2024) · Fractals · doi:10.1142/s0218348x2540047x · Cited by 2
Al-Hababi, M. A. M., Habib, A., Thabit, F., & Liu, Y. (2024) · Remote Sensing · doi:10.3390/rs16203753 · Cited by 2
A Real-time Detection Algorithm Based On Improved Nanodet For Shaft Parts
Wang, Y., & Wu, Y. (2024) · International Conference on Intelligent Human-Machine Systems and Cybernetics · doi:10.1109/ihmsc62065.2024.00047 · Cited by 2
“While one-stage algorithm omits the step of generating candidate regions and simplifies its model, which improves speed and maintain high accuracy meanwhile [2].”
BackgroundEnhanced oracle bone corrosion detection using attention-guided YOLO with ghost convolution
Gao, F., Yang, Z., Liu, Q., Zhang, Z., Li, B., & Zhang, H. (2024) · Discover Artificial Intelligence · doi:10.1007/s44163-024-00178-5 · Cited by 3
Naz, S., & Jabeen, F. (2024) · VAWKUM Transactions on Computer Sciences · doi:10.21015/vtcs.v12i2.1911 · Cited by 3
Wild Animal Species Detection System using Embedded Devices
Sridhar, P., Kabilan, V., Manikandan, R., & Mukesh Kanna, J. (2024) · International Conference on Communication and Electronics Systems (ICCES) · doi:10.1109/icces63552.2024.10859668 · Cited by 2
Prawira, N., Selviandro, N., & Wulandari, G. S. (2025) · International Conference on Advancement in Data Science, E-learning and Information System (ICADEIS) · doi:10.1109/icadeis65852.2025.10933008 · Cited by 2
“Object detection represents a fundamental aspect of autonomous vehicles [2], [3].”
InfluentialEnhanced fabric detection network with retained low-level texture features and adaptive anchors
Li, C., Huang, Z., Yu, M., & Tang, S. (2025) · Journal of Industrial Textiles · doi:10.1177/15280837251330532 · Cited by 2
“36 However, existing single-stage detectors are more effective for natural scenes than textile images due to signi fi cant differences in object attributes such as texture structure, size, and spatial distribution.”
Validating RetinaNet for the Object Detection-Based Mitosis Detection in the MIDOG Challenge
García-Salmerón, J., García, J. M., Bernabé, G., & González‐Férez, P. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-87873-2_8 · Cited by 2
García-Salmerón, J., García, J. M., Bernabé, G., & González‐Férez, P. (2025) · Berichte aus der medizinischen Informatik und Bioinformatik/Journal of integrative bioinformatics · doi:10.1515/jib-2024-0049 · Cited by 2
“The accuracy-computational trade-off is heavily influenced by the choice of the backbone network and the hyperparameter configuration [17].”
Determination of Non-Digestible Parts in Dairy Cattle Feces Using U-NET and F-CRN Architectures
Özden, C., Bulut, M., Çanga, D., & Boğa, M. (2023) · Veterinary Sciences · doi:10.3390/vetsci10010032 · Cited by 2
“These methods are defined as two-stage object detection, and the best known methods belong to the R-CNN family [40,41].”
MethodA Robust Real-time Leather Defect Segmentation Using YOLO
da Silva, V. M. M., de Pinho, R., Allahdad, M. K., Silva, J. A. M. D. C., Ferreira, M. J., & Magalhães, L. (2023) · Iberian Conference on Information Systems and Technologies (CISTI) · doi:10.23919/cisti58278.2023.10211894 · Cited by 2
“One-stage methods include a CNN that directly provides the labels [11], while the two-stage methods divide the detection process into a region proposal and a classification phase [11].”
MethodMathew, J. J., Flores, P., Das, A. K., Jiang, Y., & Zhang, Z. (2024) · Smart agriculture · doi:10.1007/978-981-97-4141-0_7 · Cited by 1
Boat Detection and Classification Framework for Safety Improvement in Port Areas
Patané, L., Maio, A., Graziani, S., & Xibilia, M. G. (2024) · IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) · doi:10.1109/metroxraine62247.2024.10796997 · Cited by 1
Research on YOLO-based Component Detection Algorithms
Zhu, H., Li, Z., Lang, Y., Li, Y., & Liu, Y. (2025) · Scientific Journal of Technology · doi:10.54691/17wnmm85 · Cited by 1
“Deep learning‐based object detection is divided into two categories based on the detection approach: two‐stage detection [3][4]and single‐stage detection[5][6].”
DFE-YOLO: A Multi-Scale-Enhanced Detection Network for Dense Object Detection in Traffic Monitoring
Li, Q., Li, Y., & Lu, Y. (2025) · Electronics · doi:10.3390/electronics14112108 · Cited by 1
MRTMD: A Multi-Resolution Dataset for Evaluating Object Detection in Traffic Monitoring Systems
Bugeja, M., Bartolo, M., Montebello, M., & Seychell, D. (2025) · IEEE Access · doi:10.1109/access.2025.3585986 · Cited by 1
“Recent comparisons of autonomous driving benchmarks also confirm that two-stage networks, such as Faster R-CNN, often outperform one-stage alternatives in terms of precision and handling minority classes, albeit with increased computational overhead [74].”
Benssalah, M., Oulahcine, D. E. R., & Drouiche, K. (2025) · International Conference on Advanced Computational Intelligence (ICACI) · doi:10.1109/icaci65340.2025.11096337 · Cited by 1
Enhanced Real-Time Highway Object Detection for Construction Zone Safety Using YOLOv8s-MTAM
Lin, W., Wang, C., Li, E.-C., & Yeh, C. (2025) · Sensors · doi:10.3390/s25206420 · Cited by 3
“…(CSP) modules to improve feature reuse and computational efficiency, while YOLOv8 adopts anchor-free prediction, decoupled classification–regression heads, and enhanced data augmentation strategies, enabling real-time inference with accuracy comparable to or exceeding that of two-stage…”
CNN-GKO-YOLOv4: an optimized neural network framework for dynamic traffic sign recognition
Vinay, P., Khan, V., M, H. K., Sharma, G., Gadhave, R. T., & Bhukya, S. (2025) · International Journal of Information Technology · doi:10.1007/s41870-025-02907-0 · Cited by 1
A vision-based explainable deep learning approach for multi-class drone detection and recognition
Samadzadegan, F., Mahini, F. A., & Gholamshahi, M. (2026) · Aerospace Science and Technology · doi:10.1016/j.ast.2026.111648 · Cited by 1
Lightweight Small-Object surface defect detection method based on improved YOLOv11
Rao, H., Zhan, H., Wang, R., & Yu, J. (2026) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-17276-y · Cited by 6
Baydilli, Y. Y. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08244-8 · Cited by 1
Tiny object detection: An in-depth survey of techniques, challenges, and future directions
Nautiyal, R., & Deshmukh, M. (2026) · Digital Signal Processing · doi:10.1016/j.dsp.2026.105995 · Cited by 4
An efficient deep learning method for pedestrian detection in high-density public places
Cao, S., Conghui, L., Ren, X., Yang, X., Zeng, Y., & Wang, P. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131878 · Cited by 1
Jin, H., Zhang, D., Liang, H., Gu, Y., & Wang, Z. (2026) · International Journal of Digital Earth · doi:10.1080/17538947.2026.2667081 · Cited by 1
Delving Into the Devils of Knowledge Distillation for Object Detection: A Survey
Shi, Q., Zhang, G., Liu, Y., Liu, Y., Zhang, W., Ze, T., & Hou, Y. (2026) · IET Computer Vision · doi:10.1049/cvi2.70067 · Cited by 1
Huang, J., Gu, B., Tang, Y., Xu, B., Li, P., Ye, J., Xu, J., & Zhang, T. (2026) · PLoS ONE · doi:10.1371/journal.pone.0348807 · Cited by 2
Vehicles Detection Using Deep Learning With Improved Single Shot Detector
Razak, M. A. A., Mahmood, N. H., Zakaria, N. A., & Othman, M. A. (2022) · International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA) · doi:10.1109/icicyta57421.2022.10038125 · Cited by 1
“However, it has high complexity and long calculation time [11-14].”
BackgroundMHCP-RCNN: Multi-Human Color Parsing Segmentation using Multi-Task Network
Abhilash, S. K., Nookala, V. M., Babu, A., Karthik, S. S., & Mithun, V. R. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191149 · Cited by 1
“Currently, the SOTA techniques are bottom-up approach [1], one-stage and two-stage approaches [2].”
MethodImproving the YOLOV7 Algorithm for Object Detection within Recorded Videos
Alrubaie, A. H., Khodher, M. A. A., & Abdulameer, A. T. (2024) · Iraqi Journal of Science · doi:10.24996/ijs.2024.65.2.35 · Cited by 1
“At a high level, current DL architectures for object detection using remote sensing camera data exhibit a common method: a convolutional backbone as a feature extractor and a sliding window prediction with a mixed regression and classification objective [19], [20].”
Algorithm for Tracking Multiple Moving Targets from a Video Feed Acquired by a Group of Drones
Mazoya, A. B., Mlyahilu, N. J., Avele, J. B. N. N., & Medfranck, M. D. O. (2024) · IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering · doi:10.1109/elcon61730.2024.10468109 · Cited by 1
“…and Transformer from different articles. a) Two-stage detectors Two-stage detector algorithms divides the object detection process into two stages, where first stage is for extraction of several regions of interests (ROI) and another stage is for classification and localization of objects[8].”
BackgroundInfluentialReal-Time Fault Detection and Condition Monitoring for Industrial Autonomous Vehicles
Thirusudhan, M., & Sasikumar, S. (2024) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-1962-8.ch004 · Cited by 2
Landing site selection for UAV in unknown environment using surface inclination
Narayan, I., Battish, N., Kaur, D., Gupta, A. K., & Poddar, S. (2024) · SPIE Future Sensing Technologies · doi:10.1117/12.3023755 · Cited by 1
Metadata
- Authors
- Carranza-García, M., Torres-Mateo, J., Lara-Benítez, P., & García-Gutiérrez, J.
- Affiliations
- Universidad de Sevilla (ES)
- Division of Computer Science, University of Sevilla, ES-41012 Seville, Spain
- Corresponding author
- Carranza-García, Manuel
- Venue
- Remote Sensing
- Publisher
- MDPI AG
- Published
- 2020-12-29
- Volume
- 13
- Issue
- 1
- Pages
- 89
- ISSN
- 2072-4292 (ISSN-L)
- OpenAlex
- W3113769242
- Cited by
- 270
- References
- 40
- Citations by year
- 2026: 34 · 2025: 62 · 2024: 75 · 2023: 42 · 2022: 40 · 2021: 17
- FWCI
- 9.63
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Remote Sensing (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Deposito de Investigacion Universidad de Sevilla (University of Seville) (submittedVersion, cc-by-nc-nd)
- Funders
- Junta de Andalucía (US-126334, P18-RT-2778)
- Ministerio de Economía y Competitividad (TIN2017-88209-C2-2-R)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- object detection, autonomous vehicles, one-stage detectors, two-stage detection, Faster R-CNN, RetinaNet, YOLOv3, FCOS, vehicle detection, pedestrian detection, cyclist detection, feature extractor, speed-accuracy trade-off, Waymo Open Dataset, real-time detection
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.