当前位置: X-MOL 学术Comput. Intell. Neurosci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
JRL-YOLO: A Novel Jump-Join Repetitious Learning Structure for Real-Time Dangerous Object Detection
Computational Intelligence and Neuroscience ( IF 3.120 ) Pub Date : 2021-04-01 , DOI: 10.1155/2021/5536152
Yiliang Zeng 1, 2, 3 , Lihao Zhang 1, 2 , Jiahong Zhao 4 , Jinhui Lan 1, 2, 3 , Biao Li 1, 2
Affiliation  

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.

中文翻译:

JRL-YOLO:一种用于实时危险物体检测的新型跳转联接重复学习结构

校园安全事件时有发生,严重影响公共安全。近年来,人工智能的飞速发展为校园智能安全带来了技术支持。为了快速识别和定位校园中的危险目标,提出了一种改进的YOLOv3-Tiny模型用于危险目标检测。由于此模型的最大优点是与YOLOv3-Tiny相比,它可以用很少的参数实现更高的精度,因此它是Tinier-YOLO模型之一。在本文中,危险目标包括危险物体和危险动作。这项工作的主要贡献包括以下几个方面:首先,将危险物体和危险动作的检测集成到一个模型中,该模型可以用较少的参数获得更高的精度。第二,为解决YOLOv3-Tiny目标检测不充分的问题,提出了一种跳跃连接重复学习(JRL)结构,并结合了空间金字塔池(SPP),它是YOLOv3-Tiny的新骨干网,可以加速YOLOv3-Tiny的骨干网络。集成不同比例尺要素的同时加快要素提取速度。最后,当两个目标距离太近时,将soft-NMS和DIoU-NMS算法结合起来,可以有效地减少漏检。对危险目标的自制数据集进行的实验测试表明,JRL-YOLO算法的平均MAP值为85.03%,比YOLOv3-Tiny增长了3.22%。在VOC2007数据集上,与使用YOLOv3-Tiny相比,该方法的检测精度提高了9.29%,与使用YOLOv4-Tiny相比,提高了2.38%,分别。这些结果都证明了该方法带来的检测精度的极大提高。此外,在测试危险目标的数据集时,JLR-YOLO的模型大小为5.84 M,大约是YOLOv3-Tiny(33.1 M)大小的五分之一,是YOLOv4-Tiny( 22.4 M)。
更新日期:2021-04-01
down
wechat
bug