Review of Target Detection Algorithms

Yingzhe Shao ； Lin Tang ； Xinyi Liu ； Hongli Wang ； Ruiyu Yang

《International Core Journal of Engineering》 8卷9期 (2022/09) Pp. 419-422

https://doi.org/10.6919/ICJE.202209_8(9).0056

摘要

The task of object detection is to find all the objects of interest in the image and determine their categories and positions, which is one of the core problems in the field of computer vision. Target detection is divided into two series -- RCNN series and YOLO series. RCNN series is a representative algorithm based on region detection. RCNN series algorithms are mainly used in target detection. The classical target detection algorithm uses the sliding window method to judge all possible regions in turn. Selective Search method is used in RCNN to extract a series of candidate regions which are more likely to be objects in advance, and then only features are extracted from these candidate regions (using CNN) for judgment.

關鍵字

Computer Vision ； Deep Learning ； Object Detection

參考文獻

Fu Huijin, Shi Tianyun, Wang Rui, Xu Chengwei, Zhang Wanpeng, Li Wentao. Research on the detection method of intruders in the perimeter of high-speed railway based on improved YOLOv5 [J/OL]. Railway Standard Design: 1-8[2022-07-22] .DOI: 10.13238/j.issn.1004-2954.202203110002.

Fu Miaomiao, Deng Miaolei, Zhang Dexian. A review of deep neural network image target detection algorithms [J]. Computer System Applications, 2022, 31(07): 35-45. DOI: 10.15888/j.cnki.csa.008595.

Ji Chaoqun. Research on Lightweight Target Detection Algorithm for Road Scenes Based on Deep Learning [D]. Changchun University of Technology, 2022. DOI: 10.27805/d.cnki.gccgy.2022.000012.

Tao Libo. Research and implementation of sensor fusion target detection algorithm based on driverless formula racing car [D]. Zhejiang University of Science and Technology, 2021. DOI: 10.27840/d.cnki. gzjkj.2021.000169.

Ji Chunsheng. Weld defect map recognition based on improved Faster R-CNN [J]. China Chemical Equipment, 2022, 24(02): 26-32+36.