Dangerous Target Recognition of Massive Image and Video Based on Deep Learning

Fu, Xiang; Ding, Guiqiang; Su, Jiongming; Zhang, Wanpeng; Gu, Xiaodong; Wu, Jianzhai

doi:10.1109/cac48633.2019.8996657

Cited by 4 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the detection effect of the model for large objects is very good, whereas the detection of small targets is not robust. YOLOv3 has been used to detect dangerous objects such as knives and guns in massive videos, which improves the detection accuracy of small targets, but the large model is difficult to be applied to small devices [ 11 ]. Hu et al [ 12 ] had good effect on small targets, but it also cannot guarantee real-time performance.…”

Section: Introductionmentioning

confidence: 99%

JRL‐YOLO: A Novel Jump‐Join Repetitious Learning Structure for Real‐Time Dangerous Object Detection

Zeng

Zhang

Zhao

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Campus security incidents occur from time to time, which seriously affect the public security. In recent years, the rapid development of artificial intelligence has brought technical support for campus intelligent security. In order to quickly recognize and locate dangerous targets on campus, an improved YOLOv3-Tiny model is proposed for dangerous target detection. Since the biggest advantage of this model is that it can achieve higher precision with very fewer parameters than YOLOv3-Tiny, it is one of the Tinier-YOLO models. In this paper, the dangerous targets include dangerous objects and dangerous actions. The main contributions of this work include the following: firstly, the detection of dangerous objects and dangerous actions is integrated into one model, and the model can achieve higher accuracy with fewer parameters. Secondly, to solve the problem of insufficient YOLOv3-Tiny target detection, a jump-join repetitious learning (JRL) structure is proposed, combined with the spatial pyramid pooling (SPP), which serves as the new backbone network of YOLOv3-Tiny and can accelerate the speed of feature extraction while integrating features of different scales. Finally, the soft-NMS and DIoU-NMS algorithm are combined to effectively reduce the missing detection when two targets are too close. Experimental tests on self-made datasets of dangerous targets show that the average MAP value of the JRL-YOLO algorithm is 85.03%, which increases by 3.22 percent compared with YOLOv3-Tiny. On the VOC2007 dataset, the proposed method has a 9.29 percent increase in detection accuracy compared to that using YOLOv3-Tiny and a 2.38 percent increase compared to that employing YOLOv4-Tiny, respectively. These results all evidence the great improvement in detection accuracy brought by the proposed method. Moreover, when testing the dataset of dangerous targets, the model size of JRL-YOLO is 5.84 M, which is about one-fifth of the size of YOLOv3-Tiny (33.1 M) and one-third of the size of YOLOv4-Tiny (22.4 M), separately.

show abstract

Section: Introductionmentioning

confidence: 99%

JRL‐YOLO: A Novel Jump‐Join Repetitious Learning Structure for Real‐Time Dangerous Object Detection

Zeng

Zhang

Zhao

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Professional training analysts, modeling the athletes based on motion sensor data, use the data of the limbs to track and correct the specifics of the athletes' motions. Because of the high price and the need for specialized motion sensors, the present sports aid system is difficult and costly for sports enthusiasts who are not professional athletes [1][2][3][4][5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

“…Recurrent neural networks are now frequently employed in machine translation, text generation, and personalized recommendation applications. Recurrent neural networks and convolutional neural networks are being combined to address the demanding problem of processing video sequences [6][7][8][9][10][11][12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

Sports Intelligent Assistance System Based on Deep Learning

2021

Scientific Programming

View full text Add to dashboard Cite

Traditional sports aid systems analyze sports data via sensors and other types of equipment and can support athletes with retrospective analysis, but they require several sensors and have limited data. This paper examines a sports aid system that uses deep learning to recognize, review, and analyze behaviors through video acquisition and intelligent video sequence processing. This paper’s primary research is as follows: (1) With an eye on the motion assistance system’s application scenarios, the network topology and implementation details of the two-stage Faster R-CNN and the single-stage YOLOv3 target detection algorithms are investigated. Additionally, training procedures are used to enhance the algorithm’s detection performance and training speed. (2) To address the issue of target detection techniques’ low detection performance in complicated backgrounds, an improved scheme from Faster R-CNN is proposed. To begin, a new approach replaces the VGG-16 network in the previous algorithm with a ResNet-101 network. Second, an expansion plan for the dataset is provided. (3) To address the short duration of action video and the high correlation of image sequence data, we present an action recognition method based on LSTM. To begin, we will present a motion decomposition scheme and evaluation index based on the key transaction frame in order to simplify the motion analysis procedure. Second, the spatial features of the frame images are extracted using a convolutional neural network. Besides, the spatial and temporal aspects of the image sequence are fused using a two-layer bidirectional LSTM network. The algorithm suggested in this research has been validated using a golf experiment, and the results are favorable.

show abstract