UA-DETRAC 2018: Report of AVSS2018 &amp; IWT4S Challenge on Advanced Traffic Monitoring

Lyu, Siwei; Chang, Ming-Ching; Du, Dawei; Li, Wenbo; Yi, Wei; Coco, Marco Del; Carcagnì, Pierluigi; Schumann, Arne; Munjal, Bharti; Dang, Dinh-Quoc-Trung; Choi, Doo−Hyun; Bochinski, Erik; Galasso, Fabio; Bunyak, Filiz; Seetharaman, Guna; Baek, Jang-Woon; Lee, Jong Taek; Palaniappan, Kannappan; Lim, Kil-Taek; Moon, Kiyoung; Kim, Kwang-Ju; Sommer, Lars; Brandlmaier, Meltem D.; Kang, Min-Sung; Jeon, Moongu; Al-Shakarji, Noor M.; Acatay, Oliver; Kim, Pyong-Kun; Amin, Sikandar; Sikora, Thomas; Dinh, Tien Ba; Senst, Tobias; Che, Vu-Gia-Hy; Lim, Young-Chul; Song, Young-min; Chung, Yun-Su

doi:10.1109/avss.2018.8639089

Cited by 53 publications

(27 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tracking Method MOTA (%) MOTP (%) Deformable Part-Based Model (DPB) [23] Globally-Optimal Greedy (GOG) [24] 26.2 76.2 ACF [25] Globally-Optimal Greedy (GOG) [24] 35.7 80.3 R-CNN [16] Discrete Continuous Tracking (DCT) [26] 38.4 80.6 Faster R-CNN [15] Multiple Hypothesis Tracking (MHT) 58.2 78.4 Evolving Boxes (EB) [27] KIOU [28] 62.1 81.9 YOLOv3 Proposed 67.6 89.1…”

Section: Detection Methodsmentioning

confidence: 99%

Online Multi-Object Tracking in Videos Based on Features Detected by YOLO

Al-Arbo¹

2021

TURCOMAT

View full text Add to dashboard Cite

With the rapid development of different applications that rely on multi-object detection and tracking, significant attention has been brought toward improving the performance of these methods. Recently, Artificial Neural Networks (ANNs) have shown outstanding performance in different applications, where objects detection and tracking are no exception. In this paper, we proposed a new object tracking method based on descriptors extracted using the convolutional filters of the YOLOv3 neural network. As these features are detected and processed during the detection phase, the proposed method has exploited these features to produce efficient and robust descriptors. The proposed method has shown better performance, compared to state-of-the-art methods, by producing better predictions using less computations. The evaluation results show that the proposed method has been able to process an average of 207.6 frames per second to track objects with 67.6% Multi-Object Tracking Accuracy (MOTA) and 89.1% Multi-Object Tracking Precision (MOTP).

show abstract

Section: Detection Methodsmentioning

confidence: 99%

Online Multi-Object Tracking in Videos Based on Features Detected by YOLO

Al-Arbo¹

2021

TURCOMAT

View full text Add to dashboard Cite

show abstract

“…This source was chosen instead of others in the literature, such as [42,58], due to the number of positive cases that the CADP dataset presents (100%) and the position of the video camera (CCTV), which allows for a thirdperson perspective. The second source used for the video dataset only contains negative cases of the presented problem, i.e., videos where no traffic accidents are presented [71]. It has a total of 100 videos from different locations in China, with a spatial resolution of 960 × 540 pixels.…”

Section: Datasetmentioning

confidence: 99%

Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques

2021

View full text Add to dashboard Cite

According to worldwide statistics, traffic accidents are the cause of a high percentage of violent deaths. The time taken to send the medical response to the accident site is largely affected by the human factor and correlates with survival probability. Due to this and the wide use of video surveillance and intelligent traffic systems, an automated traffic accident detection approach becomes desirable for computer vision researchers. Nowadays, Deep Learning (DL)-based approaches have shown high performance in computer vision tasks that involve a complex features relationship. Therefore, this work develops an automated DL-based method capable of detecting traffic accidents on video. The proposed method assumes that traffic accident events are described by visual features occurring through a temporal way. Therefore, a visual features extraction phase, followed by a temporary pattern identification, compose the model architecture. The visual and temporal features are learned in the training phase through convolution and recurrent layers using built-from-scratch and public datasets. An accuracy of 98% is achieved in the detection of accidents in public traffic accident datasets, showing a high capacity in detection independent of the road structure.

show abstract

“…Internet of Think is the medium used in sending data to the police database [65], with Internet og Think the process of recording and prosecution will be faster and can be processed immediately [66].…”

Section: Internet Of Thinkmentioning

confidence: 99%

Review of Vehicle Surveillance Using Iot in the Smart Transportation Concept

Dewi¹

2021

IJEM

View full text Add to dashboard Cite

The background of this research raises the problem of the development of smart transportation in terms of monitoring and enforcement of traffic on the highway, with the proposed system that will help many parties such as the police and the government. The system that is running is to develop a system using CCTV that is placed on every corner of the capital city to replace the police in carrying out road surveillance and law enforcement against lawbreakers, especially in the traffic sector. The method used in this research is by using literature review of many previous research journals, by reading many journals will be able to add knowledge and can deepen ongoing research. The problem raised in this research is finding solutions to problems in the transportation sector, especially smart transportation, using smart transportation will be able to connect all systems that have been made. This research produces a system proposal that can be used in further research and can be applied in terms of the development of smart cities, especially smart transportation.

show abstract

UA-DETRAC 2018: Report of AVSS2018 & IWT4S Challenge on Advanced Traffic Monitoring

Cited by 53 publications

References 16 publications

Online Multi-Object Tracking in Videos Based on Features Detected by YOLO

Online Multi-Object Tracking in Videos Based on Features Detected by YOLO

Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques

Review of Vehicle Surveillance Using Iot in the Smart Transportation Concept

Contact Info

Product

Resources

About