Detecting and Counting the Moving Vehicles Using Mask R-CNN

Lou, Lu; Zhang, Qi; Sheng, Minlan; Jun, Liu; Song, Huimin

doi:10.1109/ddcls.2019.8908877

Cited by 6 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It can be seen that the traditional method cannot track moving vehicles under the crowded environments, but our method also can performance well with a high accuracy at 92%. Compared with the method presented in [18] that was based on Mask R-CNN and Kalman Fileter, our methods are with similar accuracy, but the speed of our method is obviously higher. When images are resized to 640 * 360, the speed of whole framework (detecting, tracking and counting) of the method in [18] is about 2.86fps, while the speed of whole framework in our work is about 20fps.…”

Section: Vehicle Tracking and Counting Experimentsmentioning

confidence: 83%

“…Compared with the method presented in [18] that was based on Mask R-CNN and Kalman Fileter, our methods are with similar accuracy, but the speed of our method is obviously higher. When images are resized to 640 * 360, the speed of whole framework (detecting, tracking and counting) of the method in [18] is about 2.86fps, while the speed of whole framework in our work is about 20fps. Therefore, as for the speed of detecting and tracking, our method perform much better.…”

Section: Vehicle Tracking and Counting Experimentsmentioning

confidence: 83%

“…Compared with the traditional method [17], our method can adapt to more scenes and reach higher accuracy. Moreover, compared with the method [18] based on Mask-RCNN and Kalman Filter, our method can detect and track vehicles with much faster speed, and is more suitable for the real-time traffic monitoring system.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Detecting and Tracking the Moving Vehicles Based on Deep Learning

Jia

Wang

et al. 2021

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

Aiming to address the problem of counting multi-target moving vehicles in the various complex traffic environments, this paper proposes a detecting and tracking method based on YOLO (You Only Look Once) and Deep Sort, and evaluates its performance with public dataset (TUA-DETRAC) and two self-collection datasets. The YOLOv4 algorithm is firstly used to detect each moving vehicles, and then Deep Sort algorithm is adopted to track multi-target vehicles. The experimental results show that moving vehicles can be effectively detected and tracked in real time under different traffic environments including daytime, nighttime, rainy and crowded scenes. The experimental results show that the proposed method can reach 93% average detection accuracy with 20fps of tracking speed, and is capable of dealing with different traffic and climate conditions.

show abstract

Section: Vehicle Tracking and Counting Experimentsmentioning

confidence: 83%

Section: Vehicle Tracking and Counting Experimentsmentioning

confidence: 83%

See 1 more Smart Citation

Detecting and Tracking the Moving Vehicles Based on Deep Learning

Jia

Wang

et al. 2021

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…It can be seen from the experimental results in Table 1 that compared with previous method [17][18], our method can track and count moving vehicles in various and complex conditions. While the performance of previous method in crowded scene and large perspective is bad, and the previous method of [17] can't work in crowded weather, our method also can reach a good balance between accuracy and speed.…”

Section: Object Tracking Experimentsmentioning

confidence: 92%

Real-time detecting of urban traffic flow based on deep learning

Jia¹,

Liu²

2022

5th International Conference on Computer Information Science and Application Technology (CISAT 2022)

View full text Add to dashboard Cite

“…Two-stage detection networks represented by Fast R-CNN, Faster R-CNN, and Mask R-CNN, generally have high detection precision. However, the algorithms based on region proposals often have high complexity and long calculation time, which cannot meet the real-time requirements of vehicle detection in the actual road scenes [28][29][30]. One-stage detection network is represented by YOLO, YOLOv2, and SSD.…”

Section: Introductionmentioning

confidence: 99%

Front Vehicle Detection Algorithm for Smart Car Based on Improved SSD Model

Cao

Song

et al. 2020

Sensors

View full text Add to dashboard Cite

Vehicle detection is an indispensable part of environmental perception technology for smart cars. Aiming at the issues that conventional vehicle detection can be easily restricted by environmental conditions and cannot have accuracy and real-time performance, this article proposes a front vehicle detection algorithm for smart car based on improved SSD model. Single shot multibox detector (SSD) is one of the current mainstream object detection frameworks based on deep learning. This work first briefly introduces the SSD network model and analyzes and summarizes its problems and shortcomings in vehicle detection. Then, targeted improvements are performed to the SSD network model, including major advancements to the basic structure of the SSD model, the use of weighted mask in network training, and enhancement to the loss function. Finally, vehicle detection experiments are carried out on the basis of the KITTI vision benchmark suite and self-made vehicle dataset to observe the algorithm performance in different complicated environments and weather conditions. The test results based on the KITTI dataset show that the mAP value reaches 92.18%, and the average processing time per frame is 15 ms. Compared with the existing deep learning-based detection methods, the proposed algorithm can obtain accuracy and real-time performance simultaneously. Meanwhile, the algorithm has excellent robustness and environmental adaptability for complicated traffic environments and anti-jamming capabilities for bad weather conditions. These factors are of great significance to ensure the accurate and efficient operation of smart cars in real traffic scenarios and are beneficial to vastly reduce the incidence of traffic accidents and fully protect people’s lives and property.

show abstract

Detecting and Counting the Moving Vehicles Using Mask R-CNN

Cited by 6 publications

References 4 publications

Detecting and Tracking the Moving Vehicles Based on Deep Learning

Detecting and Tracking the Moving Vehicles Based on Deep Learning

Real-time detecting of urban traffic flow based on deep learning

Front Vehicle Detection Algorithm for Smart Car Based on Improved SSD Model

Contact Info

Product

Resources

About