Vehicle Tracking Using Deep SORT with Low Confidence Track Filtering
The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
Multi-object tracking (MOT) becomes an attractive topic due to its wide range of usability in video surveillance and traffic monitoring. Recent improvements on MOT has focused on tracking-by-detection manner. However, as a relatively complicated and integrated computer vision mission, state-of-the-art tracking-by-detection techniques are still suffering from issues such as a large number of false-positive tracks. To reduce the effect of unreliable detections on vehicle tracking, in this paper, we propose to incorporate a low confidence track filtering into the Simple Online and Realtime Tracking with a Deep association metric (Deep SORT) algorithm. We present a self-generated UA-DETRAC vehicle re-identification dataset which can be used to train the convolutional neural network of Deep SORT for data association. We evaluate our proposed tracker on UA-DETRAC test dataset. Experimental results show that the proposed method can improve the original Deep SORT algorithm with a significant margin. Our tracker outperforms the state-of-the-art online trackers and is comparable with batch-mode trackers.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Deep SORT builds upon the SORT algorithm, which excels in tracking precision and accuracy but struggles with identity switches and occlusions [44].”
From Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities (2024) · cites this paper as [44]
In the citing paper
“These recent but sophisticated tracking algorithms have improved the accuracy of object tracking, but they require heavy computational power.”
From Real-Time Vehicle Classification and Tracking Using a Transfer Learning-Improved Deep Learning Network (2022) · cites this paper as [38]
Citations
Cites
Rich 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
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Object Detection with Discriminatively Trained Part-Based Models
Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.167 · Cited by 9,853
Simple online and realtime tracking with a deep association metric
Wojke, N., Bewley, A., & Paulus, D. (2017) · 2017 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2017.8296962 · Cited by 5,286 · cited 3×
“Simple Online and Realtime Tracking with a Deep association metric (Deep SORT) from [20] by N.”
BackgroundMethodScalable 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 · cited 1×
“The images in this dataset are named by Market1501 person re-identification dataset [21] format.”
MethodSimple online and realtime tracking
Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7533003 · Cited by 4,433 · cited 1×
“The association can be done by spatial information [5, 4] or by both spatial and appearance information [6, 20, 14, 1].”
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 · cited 13×
“Experiments on UA-DETRAC test dataset shows that our proposed extension can achieve promising results by notable margins against state-of-the-art trackers.”
BackgroundMethodInfluentialGlobally-optimal greedy algorithms for tracking a variable number of objects
Pirsiavash, H., Ramanan, D., & Fowlkes, C. C. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995604 · Cited by 790 · cited 1×
“8 GOG[15] CompACT [7] Batch 14.”
High-Speed tracking-by-detection without using image information
Bochinski, E., Eiselein, V., & Sikora, T. (2017) · 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2017.8078516 · Cited by 707 · cited 2×
“in [5], detection results from consequent frames whose intersection-over-union (IOU) is larger than a threshold are associated as a track using greedy algorithm.”
BackgroundMethodChen, L., Ai, H., Zhuang, Z., & Shang, C. (2018) · 2018 IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2018.8486597 · Cited by 530
Research works printed but not linked: 1
- chen, 0, Python implementation of the kalman-iou tracker
Cited by
Adnan Yusuf, S., Khan, A., & Souissi, R. (2024) · Transportation Research Interdisciplinary Perspectives · doi:10.1016/j.trip.2023.100980 · Cited by 171
Robust Multi-Drone Multi-Target Tracking to Resolve Target Occlusion: A Benchmark
Liu, Z., Shang, Y., Li, T., Chen, G., Wang, Y., Hu, Q., & Zhu, P. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3234822 · Cited by 145
Self-citationReal-time multiple object tracking using deep learning methods
Meimetis, D., Daramouskas, I., Perikos, I., & Hatzilygeroudis, I. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06391-y · Cited by 122
“For YOLOv3-416 and 608, we are using these anchors: [10, 13], [16, 30], [33, 23], [30, 61], [62, 45], [59, 119], [116, 90], [156, 198] and [373, 326], which correspond to the size of the bounding boxes and are fundamental for the correct training of our CNN.”
BackgroundMethodZhang, S., Abdel-Aty, M. A., Cai, Q., Li, P., & Ugan, J. (2020) · Accident Analysis & Prevention · doi:10.1016/j.aap.2020.105799 · Cited by 91
Neupane, B., Horanont, T., & Aryal, J. (2022) · Sensors · doi:10.3390/s22103813 · Cited by 85
“[38] proposed the use of a method of tracking called DeepSORT with low-confidence track filtering, which reduced the false detection produced by the original DeepSORT algorithm.”
MethodEnhanced camera-based individual pig detection and tracking for smart pig farms
Guo, Q., Sun, Y., Orsini, C., Bolhuis, J. E., de Vlieg, J., Bijma, P., & de With, P. H. N. (2023) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2023.108009 · Cited by 93
Multi-object tracking in traffic environments: A systematic literature review
Jiménez-Bravo, D. M., Murciego, Á. L., Mendes, A. S., Blas, H. S. S., & Bajo, J. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.04.087 · Cited by 91
Parking Time Violation Tracking Using YOLOv8 and Tracking Algorithms
Sharma, N., Baral, S., Paing, M. P., & Chawuthai, R. (2023) · Sensors · doi:10.3390/s23135843 · Cited by 78
“Object tracking has been used in many domains such as pedestrian tracking [31], vehicle tracking [32], and player tracking [33].”
MethodVelastin, S. A., Fernández, R., Espinosa, J. E., & Bay, A. (2020) · Sensors · doi:10.3390/s20216251 · Cited by 61
“For vehicle tracking, deep features are associated combining point tracking and object appearance as, for example, done by Hou et al. [48] with D-SORT to track vehicles.”
MethodWutke, M., Heinrich, F., Das, P. P., Lange, A., Gentz, M., Traulsen, I., Warns, F. K., Schmitt, A. O., & Gültaş, M. (2021) · Sensors · doi:10.3390/s21227512 · Cited by 66
“Although the most successful tracking approaches are based on a TBD-strategy, the consequence of missing detections can be a significant reduction in their performance [53].”
BackgroundReal-Time Detection of Microplastics Using an AI Camera
Sarker, M. A. B., Imtiaz, M. H., Holsen, T. M., & Baki, A. B. M. (2024) · Sensors · doi:10.3390/s24134394 · Cited by 69
“…online real-time Tracking (DeepSORT) is one of the multi-object tracking (MOT) algorithms that has been used in underwater object tracking [25–28], vehicle tracking [29], unmanned vehicle tracking (UAV) [30], athletics [31], robotics [32], population tracking [33], and cotton seed count [34].”
BackgroundTracklets Predicting Based Adaptive Graph TrackingPreprint
Shan, C., Wei, C., Deng, B., Huang, J., Hua, X., Cheng, X., & Liang, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.09015 · Cited by 65
Drone mapping of damage information in GPS-Denied disaster sites
Nath, N. D., Cheng, C., & Behzadan, A. H. (2021) · Advanced Engineering Informatics · doi:10.1016/j.aei.2021.101450 · Cited by 59
Object tracking and counting in a zone using YOLOv4, DeepSORT and TensorFlow
Kumar, S., Vishal, Sharma, P. R., & Pal, N. (2021) · International Conference on Artificial Intelligence and Smart Energy (ICAIS) · doi:10.1109/icais50930.2021.9395971 · Cited by 51
“We use DeepSORT with YOLO to detect and track multiple objects based on various attributes of the objects such as the size of the object, velocity of object, shape and physical appearance of the object etc[10].”
MethodTowards AI-Based Traffic Counting System with Edge Computing
Dinh, D.-L., Nguyen, H.-N., Thai, H.-T., & Le, K.-H. (2021) · Journal of Advanced Transportation · doi:10.1155/2021/5551976 · Cited by 48
“e outstanding feature in Deep SORT is to integrate an appearance descriptor, which is a wide residual network, with two convolutional layers followed by six residual blocks [63].”
BackgroundDeep Learning-Based Computer Vision for Surveillance in ITS: Evaluation of State-of-the-Art Methods
Xie, J., Zheng, Y., Du, R., Xiong, W., Cao, Y., Ma, Z., Cao, D., & Guo, J. H. (2021) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3065250 · Cited by 52
Zhu, D., Sze, N. N., Feng, Z., & Yang, Z. (2021) · Safety Science · doi:10.1016/j.ssci.2021.105600 · Cited by 40
Multiple Object Tracking in Robotic Applications: Trends and Challenges
Gad, A., Basmaji, T., Yaghi, M., Alheeh, H., AlKhedher, M. A., & Ghazal, M. A. (2022) · Applied Sciences · doi:10.3390/app12199408 · Cited by 38
“[69] added the deep_sort algorithm to the extracted features to reduce the unreliable tracks, and Ref.”
MethodPatel, D., Hosseini, P., & Jalayer, M. (2023) · Accident Analysis & Prevention · doi:10.1016/j.aap.2023.107264 · Cited by 36
Ngeni, F., Mwakalonge, J., & Siuhi, S. (2024) · Journal of Traffic and Transportation Engineering (English Edition) · doi:10.1016/j.jtte.2023.05.006 · Cited by 43
CLONE: Collaborative Learning on the Edges
Lu, S., Yao, Y., & Shi, W. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3030278 · Cited by 31
“2) Experiment Setup: We employed YOLOv3 [72] and Deep SORT algorithms [76] to detect person and then achieve multi-target tracking.”
MethodA Real-Time Safety-Based Optimal Velocity Model
Abdelhalim, A., & Abbas, M. M. (2022) · IEEE Open Journal of Intelligent Transportation Systems · doi:10.1109/ojits.2022.3147744 · Cited by 36
Achieving Adaptive Visual Multi-Object Tracking with Unscented Kalman Filter
Zhang, G., Yin, J., Deng, P., Sun, Y., Zhou, L., & Zhang, K. (2022) · Sensors · doi:10.3390/s22239106 · Cited by 32
“Although some studies have improved the DeepSORT algorithm, as shown in [17], which is proposed to combine low confidence trajectory filtering and depth correlation measurement (depth ranking) algorithm into simple online real-time tracking.”
MethodDeep Learning-Based Real-Time Traffic Sign Recognition System for Urban Environments
Kim, C.-I., Park, J., Park, Y., Jung, W., & Lim, Y. (2023) · Infrastructures · doi:10.3390/infrastructures8020020 · Cited by 32
Yang, J., Bao, Y., Sun, Z., & Meng, X. (2024) · Sustainability · doi:10.3390/su16031081 · Cited by 29
“Unlike detection-point tracking, the updated algorithms, such as Simple Online and Realtime Tracking (SORT) and DEEPSORT [32,33], make maximum use of the visual data on the vehicles and take the attributes from the object bounding box as the state predictions of the Kalman filter to ensure the…”
MethodA New Real-Time Detection and Tracking Method in Videos for Small Target Traffic Signs
Song, S., Li, Y., Huang, Q., & Li, G. (2021) · Applied Sciences · doi:10.3390/app11073061 · Cited by 27
Smart Traffic Monitoring System using YOLO and Deep Learning Techniques
Kalva, A. R., Chelluboina, J. S., & Bharathi, B. (2023) · International Conference on Trends in Electronics and Informatics (ICOEI) · doi:10.1109/icoei56765.2023.10126048 · Cited by 26
“This helps to ensure that the model only makes predictions for objects about which it is very confident and that it is not affected by false positive detections [16].”
BackgroundPronello, C., & Garzón Ruiz, X. R. (2023) · Sensors · doi:10.3390/s23187719 · Cited by 24
Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities
Karim, A., Raza, M. A., Alharthi, Y. Z., Abbas, G., Othmen, S., Hossain, M. S., Nahar, A., & Mercorelli, P. (2024) · World Electric Vehicle Journal · doi:10.3390/wevj15090382 · Cited by 23
Lashkov, I., Yuan, R., & Zhang, G. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.126240 · Cited by 24
Zadobrischi, E. (2022) · Sensors · doi:10.3390/s22207861 · Cited by 23
“The learning ability of residuals aims to simplify the degree of complexity of the training process and improve detection [60].”
BackgroundAnalyzing Nitrogen Effects on Rice Panicle Development by Panicle Detection and Time-Series Tracking
Zhou, Q., Guo, W. F., Chen, N., Wang, Z., Li, G., Ding, Y., Ninomiya, S., & Mu, Y. (2023) · Plant Phenomics · doi:10.34133/plantphenomics.0048 · Cited by 20
“The algorithm achieves a relatively stable tracking effect and is widely used in the tracking and detection of industrial targets, such as vehicles and pedestrians [27,28].”
MethodXu, Z., Wei, B., & Zhang, J. (2023) · Structures · doi:10.1016/j.istruc.2023.05.023 · Cited by 23
Vision-based Object Tracking in Marine Environments using Features from Neural Network Detections
Schöller, F. E. T., Blanke, M., Plenge-Feidenhans’l, M. K., & Nalpantidis, L. (2020) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2020.12.1455 · Cited by 27
Kalliovaara, J., Jokela, T., Asadi, M., Majd, A., Hallio, J., Auranen, J., Seppänen, M., Putkonen, A., Koskinen, J., Tuomola, T., et al. (2024) · Remote Sensing · doi:10.3390/rs16091545 · Cited by 17
Deep learning-based few-shot person re-identification from top-view RGB and depth images
Abed, A., Akrout, B., & Amous, I. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10239-6 · Cited by 18
Automated Traffic Surveillance Using Existing Cameras on Transit Buses
Redmill, K., Yurtsever, E., Mishalani, R. G., Coifman, B. A., & McCord, M. R. (2023) · Sensors · doi:10.3390/s23115086 · Cited by 16
“Deep-SORT-based vehicle detectors [24] can achieve state-of-the-art performance.”
BackgroundRecent Technology Advancements in Smart City Management: A Review
Tavares, J. M. R. S., Chiranjeevi, K., Machado, J. J. M., Jain, D. K., Dannana, S., Gottapu, S. K., & Gandomi, A. H. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.058461 · Cited by 21
Autonomous vehicle surveillance through fuzzy C-means segmentation and DeepSORT on aerial images
Qureshi, A. M., Alotaibi, M., Alotaibi, S. R., AlHammadi, D. A., Jamal, M. A., Jalal, A., & Lee, B. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.2835 · Cited by 15
“To track the movement of vehicles frame by frame, we implemented DeepSORT ( Wojke, Bewley & Paulus, 2017 ; Hou, Wang & Chau, 2019 ; Kapania et al., 2020 ; Pramanik et al., 2022 ).”
Feng, Y., Zhao, Y., Zhang, X., Batista, S., Demiris, Y., & Angeloudis, P. (2024) · Transportmetrica B Transport Dynamics · doi:10.1080/21680566.2024.2380915 · Cited by 16
“Neverthe-less, as Table 1 indicates, several recent studies have used these datasets, showcasing their potential in developing models for traffic flow prediction and accident detection (Hou, Wang, and Chau 2019; Srinivasan et al. 2020; Thakare et al. 2022).”
A conflict risk graph approach to modeling spatio-temporal dynamics of intersection safety
Wang, T., Ge, Y.-E., Wang, Y., Prato, C. G., Chen, W., & Niu, Y. (2024) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2024.104874 · Cited by 14
Self-citationPapakis, I., Sarkar, A., & Karpatne, A. (2021) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc48978.2021.9564655 · Cited by 16
Traffic Signal Transition Time Prediction Based on Aerial Captures during Peak Hours
Luo, R., & Su, R. (2020) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv50220.2020.9305382 · Cited by 13
“The SORT algorithm builds a similarity matrix through the Intersection over Union (IOU) of sequential frames, so the SORT calculation speed is very fast [21].”
MethodHyperion: A Robust Drone-based Target Tracking System
Anastasiou, A., Makrigiorgis, R., Kolios, P., & Panayiotou, C. G. (2021) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas51884.2021.9476687 · Cited by 12
Vehicular/Non-Vehicular Multi-Class Multi-Object Tracking in Drone-Based Aerial Scenes
Bisio, I., Garibotto, C., Haleem, H., Lavagetto, F., & Sciarrone, A. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3332132 · Cited by 13
Identification of Driver Phone Usage Violations via State-of-the-Art Object Detection with Tracking
Carrell, S., & Atapour–Abarghouei, A. (2021) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata52589.2021.9671378 · Cited by 13
“The DeepSort [14] tracking algorithm is also integrated into this system.”
BackgroundMethodInfluentialLong-Range Multi-Object Tracking at Traffic Intersections on Low-Power Devices
Emami, P., Elefteriadou, L., & Ranka, S. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3115513 · Cited by 15
Deep Learning Based Real-Time Biodiversity Analysis Using Aerial Vehicles
Panigrahi, S., Maski, P., & Thondiyath, A. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-030-97672-9_36 · Cited by 11
Deep Learning-based Trajectory Estimation of Vehicles in Crowded and Crossroad Scenarios
Siddique, A., & Afanasyev, I. M. (2021) · Conference of Open Innovations Association (FRUCT) · doi:10.23919/fruct50888.2021.9347580 · Cited by 11
“Some work in the field of trajectory estimation of vehicles can be found in [10], [11], [18]–[20].”
BackgroundSFFSORT Multi-Object Tracking by Shallow Feature Fusion for Vehicle Counting
Zhonglin, T., Wahab, M. N. A., Akbar, M. F., Mohamed, A. S. A., Noor, M. H. M., & Rosdi, B. A. (2023) · IEEE Access · doi:10.1109/access.2023.3297190 · Cited by 11
“To manage occlusions, appearance changes, and track fragmentation, various methods, such as Hungarian algorithm-based data association [46] and Deep SORT [47], have been developed.”
BackgroundReyna, A. H., Farfán, A. J. F., Filho, G. P. R., Sampaio, S., Grande, R. E. D., Nakamura, L. H. V., & Meneguette, R. I. (2024) · Journal of Internet Services and Applications · doi:10.5753/jisa.2024.3809 · Cited by 11
Ren, Q., He, J., Liu, Z., & Xu, M. G. (2024) · Asian Transport Studies · doi:10.1016/j.eastsj.2024.100138 · Cited by 11
Drone Swarm for Distributed Video Surveillance of Roads and Car Tracking
Pedroche, D. S., Amigo, D., García, J., Molina, J. M., & Zubasti, P. (2024) · Drones · doi:10.3390/drones8110695 · Cited by 10
“Typical approaches in the tracking field include the use of algorithms like DeepSORT [25], Kalman filter [58] and its improvements [54], and more advanced filters like the Interacting Multiple Model (IMM) [59,60] or particle filters [61].”
Vehicle Analysis System Based on DeepSORT and YOLOv5
Guo, F., & Xu, Y. (2022) · 2022 3rd International Conference on Computer Vision, Image and Deep Learning & International Conference on Computer Engineering and Applications (CVIDL & ICCEA) · doi:10.1109/cvidliccea56201.2022.9824363 · Cited by 10
Adaptive Kalman Filter with power transformation for online multi-object tracking
Liu, Y., Li, Y., Xu, D., Yang, Q., & Tao, W. (2023) · Multimedia Systems · doi:10.1007/s00530-023-01052-7 · Cited by 13
“In fact, most methods [10, 16, 21, 22] adopt a similar design, but low-score detection boxes usually involve high-level occlusion noise [15, 18, 22].”
MethodHM-Net: A Regression Network for Object Center Detection and Tracking on Wide Area Motion Imagery
Motorcu, H., Ateş, H. F., Uğurdağ, H. F., & Gunturk, B. K. (2021) · IEEE Access · doi:10.1109/access.2021.3138980 · Cited by 10
“In tracking-bydetection approach, most trackers [17], [18], [20] utilize”
BackgroundOpportunities and Challenges in Vehicle Tracking: A Computer Vision-Based Vehicle Tracking System
Zarindast, A., & Sharma, A. (2023) · Data Science for Transportation · doi:10.1007/s42421-023-00063-0 · Cited by 10
“Hou et al. 2019 proposed an extension on Deep SORT algorithm where tracks with low detection confidence on their initial frames will be deleted.”
BackgroundHonarparvar, S., Saeedi, S., Liang, S. H. L., & Squires, J. (2021) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi10020081 · Cited by 9
“Deep simple online and real-time tracking (DeepSORT) is one of the algorithms used in vehicle tracking [50], pedestrian tracking [51], ball tracking [52], etc.”
MethodEnhanced deep OC-SORT with YOLOv8-seg for robust fry tracking and behavior analysis in aquaculture
Xi, C., Cui, M., Yin, J., Gu, H., Ouyang, T., Feng, J., & Zeng, L. (2025) · Aquaculture · doi:10.1016/j.aquaculture.2025.742887 · Cited by 8
Implementation of an improved multi-object detection, tracking, and counting for autonomous driving
Albouchi, A., Messaoud, S., Bouaafia, S., Hajjaji, M. A., & Mtibaa, A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17444-w · Cited by 10
Kim, J.-H., Lee, M., & Lee, T.-S. (2022) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2022-spring54318.2022.9860725 · Cited by 8
“Since the performance of the common D-SORT is limited by the false-positive cases created by unreliable objects, inspired by [17], we improve the common D-SORT via adding a two-stage low-confidence filtering (LCF).”
MethodArtificial Intelligence (AI) based Detection of Traffic Violations by Two-Wheeler Vehicles
Kishore, M., Reddy, I. S., Sujihelen, L., Sivasangari, A., & Christy, A. (2023) · International Conference on Intelligent Computing and Control Systems (ICICCS) · doi:10.1109/iciccs56967.2023.10142605 · Cited by 8
“Consequently, it is crucial to develop an Automatic License Plate Detection and Recognition (ALPDR) model that can identify a vehicle's license plate number automatically[11][12].”
BackgroundZhao, W., Yang, G., Xia, T., Chen, F., Zheng, N., & Ren, P. (2023) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2023.3327110 · Cited by 8
“Digital Object Identifier 10.1109/TVLSI.2023.3327110 classification [1], obstacle detection [2], lane detection [3], and tracking [4], they are increasingly being adopted in place of traditional perception algorithms for autonomous driving.”
BackgroundInfluentialA Review On Emotion Identification Using YOLO and DeepSORT
Goel, A., Karim, R., Singh, U. K., & Kumar, R. (2024) · IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT) · doi:10.1109/ic2pct60090.2024.10486695 · Cited by 8
“A study by Hou et al. [10] focused on vehicle tracking by suggesting a novel approach in improving the Deep SORT algorithm for multi-object tracking.”
MethodA review of object tracking based on deep learning
Zhao, G., Meng, F., Yang, C., Wei, H., Zhang, D., & Zheng, Z. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130988 · Cited by 7
Chang, B. R., Tsai, H. F., & Chen, C. H. (2026) · Electronics · doi:10.3390/electronics15020353 · Cited by 9
Abdelhalim, A., Abbas, M. M., Kotha, B. B., & Wicks, A. L. (2021) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc48978.2021.9564525 · Cited by 7
No, W., Noh, B., & Kim, Y. (2024) · Advances in Engineering Software · doi:10.1016/j.advengsoft.2024.103687 · Cited by 6
Cai, H., Lin, H., & Liu, D. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01407-8 · Cited by 7
“In contrast, some works improve the tracking performance under vehicle occlusion by training an additional vehicle re-identification network [2, 14].”
Indoor Distance Measurement System COPS (COVID-19 Prevention System)
Shin, M., & Moon, N. (2021) · Sustainability · doi:10.3390/su13094738 · Cited by 6
“Hou improved lowreliability tracking filtering using the DeepSORT algorithm to reduce the influence of unreliable detection on vehicle tracking [25].”
MethodWang, W., Xie, Y., & Tang, L. (2023) · Sensors · doi:10.3390/s23156909 · Cited by 6
“SORT [53].”
MethodComputing with Words in Maritime Piracy and Attack Detection Systems
Tešić, J., Tamir, D. E., Neumann, S., Rishe, N. D., & Kandel, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-50439-7_30 · Cited by 6
“Pascal VOC, COCO, and ImageNet [9], and benchmarks motivated a breakthroughs in the field as training samples were collected via a well-executed and expensive crowd sourcing endeavor to label millions of object instances in imagery created by consumers using their hand-held devices.”
BackgroundQuang, P. H., Thanh, P. P., Anh, T. N. V., Phi, S. V., Nhat, B. L., & Trong, H. N. (2021) · International Conference on Advanced Computing and Applications (ACOMP) · doi:10.1109/acomp53746.2021.00015 · Cited by 5
Research on vehicle target detection technology based on UAV aerial images
Liu, W., Wang, M., Zhang, S., & Zhou, P. (2022) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma54519.2022.9856250 · Cited by 5
“DeepSORT[11] is an updated version of SORT, which integrates appearance information to improve the performance of SORT, which allows the target to be tracked properly even during prolonged occlusions and effectively reduces the number of ID transitions that occur.”
BackgroundMultiple-Vehicle Tracking in the Highway Using Appearance Model and Visual Object Tracking
Bafghi, F., & Shoushtarian, B. M. (2020) · Iranian Conference on Machine Vision and Image Processing · doi:10.1109/mvip49855.2020.9116905 · Cited by 5
“This network can be a simple YOLO as in [16] or a re-identification CNN as in [17].”
MethodLiu, B., Qian, Y., & Wang, J. (2023) · BMC Neuroscience · doi:10.1186/s12868-023-00787-3 · Cited by 5
“This state-of-the-art method of Multiple Object Tracking (MOT) has been widely implemented in the tracking of pedestrians [14], vehicles [15], and animals in complex environments [16, 17, 20].”
MethodComputer Vision Based Traffic Monitoring System
Bhasin, S., Saini, S., Gupta, D., & Mann, S. (2024) · International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) · doi:10.1109/icrito61523.2024.10522331 · Cited by 5
“[3] License plate recognition is integral to traffic management systems for vehicle identification and law enforcement.”
BackgroundVehicle Speed Calculation from Drone Video Based on Deep Learning
Rahman, T., Siregar, M. A. L., Kurniawan, A., Juniastuti, S., & Yuniarno, E. M. (2020) · 2020 International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM) · doi:10.1109/cenim51130.2020.9297844 · Cited by 4
“SORT uses constant speed and linear observations to determine the position of each existing path based on the location of coordinates before and after the frame changes [10].”
MethodMulti-pedestrian Tracking and Person Re-identification
Nissimagoudar, P. C., Iyer, N. C., Gireesha, H. M., Pillai, P. S., & Mallapur, S. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-030-96302-6_16 · Cited by 4
Group-of-Picture Mode Acceleration for Efficient Object Detection in Video Streams
Chen, K.-H. (2023) · IEEE Access · doi:10.1109/access.2023.3294558 · Cited by 4
“Reference [24] shows that Deep SORT can be applied in vehicle tracking.”
Divyaprabha, D., & Seebaiah, G. (2024) · International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering · doi:10.11591/ijece.v14i5.pp5681-5690 · Cited by 3
“Also there exist various algorithms which only uses motion cues in contrast to increase the speed of algorithm but cannot properly handle occlusions and person re-identification identify the lost objects as shown in the studies by [20]–[22].”
BackgroundMultiscale Collaborative Attention Network for Robust Multiobject Tracking in Satellite Video
Hu, F., Yang, P., Dou, J., & Dou, L. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3626807 · Cited by 3
“It takes therefineddetectionsfromStage2asinputandemploysaSORT-based [30]”
Pedestrian Behavior Analytics on Dashcam Videos in Chaotic Environments
Mukherjee, P., & Lall, B. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3062762 · Cited by 3
SIVD: Dataset of Iranian Vehicles for Real-Time Multi-Camera Video Tracking and Recognition
Siahkali, F., Alavi, S. A., & Masouleh, M. T. (2022) · Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS) · doi:10.1109/icspis56952.2022.10043932 · Cited by 3
“In [16], a low confidence track filter is proposed based on the DeepSORT [12] algorithm, which significantly reduces the false positive tracks in the initial tracking frames.”
MethodDetection, Classification and Counting of Moving Vehicles from Videos
Sunny, A., & Manohar, N. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-6346-1_19 · Cited by 3
Real Time Video Object Detection Using Deep Learning
Sharma, K., Sahu, T. K., Bhatt, P., Singh, A., & Bhatia, M. (2023) · International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT) · doi:10.1109/icaiccit60255.2023.10466207 · Cited by 3
“Hou et al. [18] focused on tracking-by-detection, which attempts to improve multi-object tracking (MOT) for uses including traffic monitoring and video surveillance.”
BackgroundHeavy Vehicle Classification Through Deep Learning
Sun, P.-Y., Sun, W.-Y., Jin, Y., & Sinnott, R. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59612-5_16 · Cited by 4
MOTrack: Real-time Configuration Adaptation for Video Analytics through Movement Tracking
Wu, F., Gao, L., Zhou, T., & Wang, X. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685159 · Cited by 3
“Traffic tracking localizes and tracks the pedestrian and vehicles indoors or outdoors from videos based on the DeepSort model [12].”
MethodSignal Synchronization of Traffic Lights Using Reinforcement Learning
Aydın, İ., Sevi, M., Gungoren, G., & Irez, H. C. (2022) · International Conference on Data Analytics for Business and Industry (ICDABI) · doi:10.1109/icdabi56818.2022.10041559 · Cited by 3
“In studies, we were satisfied with the performance of YOLOv4, and it was observed that it works fast and with high accuracy [6-9].”
MethodYOLOV4 Deepsort ANN for Traffic Collision Detection
Nurdin, A., Aji, B. A. S., Sudianto, Y., & Rafrin, M. (2023) · Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI) · doi:10.23887/janapati.v12i3.62923 · Cited by 2
Comprehensive Analysis of YOLOv8 + DeepSORT for Vehicle Tracking: HOTA and CLEAR-Based Evaluation
Indrayana, I. N. E., Sudarma, M., Putra, I. K. G. D., & Sudana, O. (2025) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2025.0160940 · Cited by 2
“…Realtime Tracking) algorithm, developed by Bewley in 2016, provides an efficient solution for the multiple object tracking (MOT) task by employing object detection and a Kalman filter for movement prediction, alongside the Hungarian algorithm for associating detections across successive frames [8].”
An efficient hybrid approach for vehicle detection and tracking
El-Alami, A., Nadir, Y., Amhaimar, L., & Mansouri, K. (2023) · International Conference on Wireless Networks and Mobile Communications (WINCOM) · doi:10.1109/wincom59760.2023.10322924 · Cited by 2
“For vehicle tracking, several studies have proposed hybrid approaches that uses deep learning models such as YOLO, SSD or other traditional detection pipelines for initial detection, followed by tracking algorithms for data association such as SORT or DeepSORT [25]–[28].”
MethodYelure, B. S. (2024) · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · doi:10.55041/ijsrem36018 · Cited by 2
Improving Performance of CNN Based Vehicle Detection and Tracking by Median Algorithm
Shah, R. A., Urmonov, O., & Kim, H. (2021) · IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia) · doi:10.1109/icce-asia53811.2021.9641942 · Cited by 2
A Fast Multi-Object Tracking Method using DDR Descriptor
Leewan, K., Jongsawat, N., & Tungkasthan, A. (2021) · International Conference on ICT and Knowledge Engineering · doi:10.1109/ictke52386.2021.9665699 · Cited by 2
Runtime Anomaly Monitoring of Human Perception Models for Robotic Systems
Arunachalam, H., Huang, Z., Hanheide, M., & Guevara, L. (2024) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case59546.2024.10711500 · Cited by 1
“The method used to track the bounding boxes can be any generic object tracker as the ones used in [12], [13] that can generate as output, a subset from the detected bounding boxes.”
MethodRadar-Camera Extrinsic Calibration for Roadside Infrastructure: A Systematic Review
Rokhi, Z., & Emadi, A. (2026) · Vehicles · doi:10.3390/vehicles8060137 · Cited by 1
“Once detections are obtained, multi-object tracking methods commonly use trackers such as SORT [103,104] or its deep-learning variant, such as StrongSORT [105] or DeepSORT [106], to maintain trajectories over time.”
High-Level Feature Extraction for Crowd Behaviour Analysis: A Computer Vision Approach
Bruno, A., Ferjani, M., Sabeur, Z. A., Arbab‐Zavar, B., Çetinkaya, D., Johnstone, L., Sallal, M., & Benaouda, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-13324-4_6 · Cited by 1
“Inspired by Hou et al.’s method [12] on vehicle tracking, the first of two deep learning modules sees the integration of two popular models such as YOLOv5 [13] and DeepSORT [26].”
MethodResearch on the Simulation Test Method of Autonomous Driving Vehicle Based on Cloud Platform
Shen, Y., Hou, Q., Wang, J., & Zhu, X. (2022) · Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) · doi:10.1109/acirs55390.2022.9845548 · Cited by 1
“The Deep Sort algorithm is one of the commonly used multitarget tracking algorithms [13].”
MethodPerformance Evaluation of Visual Object Tracking using YOLO Deep SORT with LCF
Maung, K. O., & Myint, T. (2022) · International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) · doi:10.1109/itc-cscc55581.2022.9894855 · Cited by 1
“A low confidence track filtering (LCF) is extended on Deep SORT tracking algorithm for the purpose of significantly reducing false positive tracks generated by Deep SORT [7].”
Method
Metadata
- Authors
- Hou, X., Wang, Y., & Chau, L.-P.
- Affiliations
- Nanyang Technological University (SG)
- Venue
- 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
- Publisher
- IEEE
- Published
- 2019-09
- Pages
- 1-6
- OpenAlex
- W2991384465
- Cited by
- 123
- References
- 21
- Citations by year
- 2026: 6 · 2025: 8 · 2024: 26 · 2023: 29 · 2022: 19 · 2021: 25 · 2020: 10
- FWCI
- 4.40
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) (publishedVersion)
- 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
- vehicle tracking, multi-target tracking, data association, tracking-by-detection, UA-DETRAC, vehicle re-identification, online tracking
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.