A New Real-Time Detection and Tracking Method in Videos for Small Target Traffic Signs

Song, Shaojian; Li, Yuanchao; Huang, Qingbao; Li, Gang

doi:10.3390/app11073061

Cited by 21 publications

(9 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Likewise, Song et al [12], improved the version of YOLOv3 and incorporated Deep-Sort into the method of detection and tracking. Deep-Sort accuracy, recall and mAP (mean average precision) respectively was (91%, 90%, and 84.76%).…”

Section: Transfer Learningmentioning

confidence: 99%

“…In a study of the real-time detection and tracking of small Target Traffic Signs, Song et al 2021 [12], proposed also an improved version of YOLOv3. After working on data augmentation to address the problem of the unbalanced sampling distribution (a mechanism we used), the remarkable thing about their improvement of the YOLO algorithm is the removal of the corresponding output To reduce its computational costs and improve real-time, the most important point here is to incorporate Deep-Sort into the detection method to improve the accuracy and robustness of multi-object detection and improve tracking in videos, and the work showed improvement in accuracy, recall and mAP respectively (91%, 90%, and 84.76%).…”

Section: Pedestrians Trackingmentioning

confidence: 99%

See 1 more Smart Citation

Improve Detection and Tracking of Pedestrian Subclasses by Pre-Trained Models

Sukkar

Kumar

Sindha

2022

J. ADV. ENG. COMPUT.

View full text Add to dashboard Cite

There are sub-classes of pedestrians that can be defined and it is important to distinguish between them for the detection in autonomous vehicle applications, such as elderly, and children, to reduce the risk of collision. It is necessary to talk about effective pedestrian tracking besides detection so that object remains accurately monitored, here the effective pre-trained algorithms come to achieve this goal in real-time. In this paper, we make a comparison between the detection and tracking algorithms, we applied the transfer learning technique to train the detection model on new sub-classes, after making Images augmentation in previous work, we got better results in detection, reached 0.81 mAP in real-time by using Yolov5 model, with a good tracking performance by the tracking algorithm dependent on detection Deep-SORT.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.

show abstract

Section: Transfer Learningmentioning

confidence: 99%

Section: Pedestrians Trackingmentioning

confidence: 99%

Improve Detection and Tracking of Pedestrian Subclasses by Pre-Trained Models

Sukkar

Kumar

Sindha

2022

J. ADV. ENG. COMPUT.

View full text Add to dashboard Cite

show abstract

“…Song et al tracked objects from self-driving vehicles to Deepsort using YOLOv3 [103]. In YOLOv3, they removed 32-times subsampling and added four-times subsampling for traffic signs.…”

Section: Detection and Predictionmentioning

confidence: 99%

Multiple Object Tracking in Deep Learning Approaches: A Survey

et al. 2021

View full text Add to dashboard Cite

Object tracking is a fundamental computer vision problem that refers to a set of methods proposed to precisely track the motion trajectory of an object in a video. Multiple Object Tracking (MOT) is a subclass of object tracking that has received growing interest due to its academic and commercial potential. Although numerous methods have been introduced to cope with this problem, many challenges remain to be solved, such as severe object occlusion and abrupt appearance changes. This paper focuses on giving a thorough review of the evolution of MOT in recent decades, investigating the recent advances in MOT, and showing some potential directions for future work. The primary contributions include: (1) a detailed description of the MOT’s main problems and solutions, (2) a categorization of the previous MOT algorithms into 12 approaches and discussion of the main procedures for each category, (3) a review of the benchmark datasets and standard evaluation methods for evaluating the MOT, (4) a discussion of various MOT challenges and solutions by analyzing the related references, and (5) a summary of the latest MOT technologies and recent MOT trends using the mentioned MOT categories.

show abstract

“…Presently, the majority of researchers focus on improving the static detection effect of different fruit targets [20][21][22]. However, related studies on the dynamic tracking and accurate counting of green citrus have seen less attention.…”

Section: Introductionmentioning

confidence: 99%

Green Citrus Detection and Counting in Orchards Based on YOLOv5-CS and AI Edge System

Lyu

Zhao

et al. 2022

Sensors

View full text Add to dashboard Cite

Green citrus detection in citrus orchards provides reliable support for production management chains, such as fruit thinning, sunburn prevention and yield estimation. In this paper, we proposed a lightweight object detection YOLOv5-CS (Citrus Sort) model to realize object detection and the accurate counting of green citrus in the natural environment. First, we employ image rotation codes to improve the generalization ability of the model. Second, in the backbone, a convolutional layer is replaced by a convolutional block attention module, and a detection layer is embedded to improve the detection accuracy of the little citrus. Third, both the loss function CIoU (Complete Intersection over Union) and cosine annealing algorithm are used to get the better training effect of the model. Finally, our model is migrated and deployed to the AI (Artificial Intelligence) edge system. Furthermore, we apply the scene segmentation method using the “virtual region” to achieve accurate counting of the green citrus, thereby forming an embedded system of green citrus counting by edge computing. The results show that the mAP@.5 of the YOLOv5-CS model for green citrus was 98.23%, and the recall is 97.66%. The inference speed of YOLOv5-CS detecting a picture on the server is 0.017 s, and the inference speed on Nvidia Jetson Xavier NX is 0.037 s. The detection and counting frame rate of the AI edge system-side counting system is 28 FPS, which meets the counting requirements of green citrus.

show abstract

A New Real-Time Detection and Tracking Method in Videos for Small Target Traffic Signs

Cited by 21 publications

References 52 publications

Improve Detection and Tracking of Pedestrian Subclasses by Pre-Trained Models

Improve Detection and Tracking of Pedestrian Subclasses by Pre-Trained Models

Multiple Object Tracking in Deep Learning Approaches: A Survey

Green Citrus Detection and Counting in Orchards Based on YOLOv5-CS and AI Edge System

Contact Info

Product

Resources

About