Litcius/Paper detail

TS-YOLO:An efficient YOLO Network for Multi-scale Object Detection

Yang Wang, Bo Ding, Li Su Tong

20222022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)23 citationsDOI

Abstract

To solve the problem that the You Only Look Once(YOLO) v4 still has missing detection in multi-scale object detection, we proposed a novel deep convolutional network structure TS-YOLO with three spatial pyramid pooling(SPP) modules in YOLOv4. SPP plays an important role in multi-scale object detection, it can extract more semantic information in complex scenes. In this paper, we add two more SPP modules and redesign the pooling core sizes in SPP on the basis of YOLOv4. Our training was on the Pascal VOC data set and the experimental results show that our TS-YOLO not only detects more objects but also has 2.21% higher accuracy compared with original YOLOv4, demonstrating the excellent performance of our model in multi-scale object detection.

Topics & Concepts

Object detectionPascal (unit)Computer sciencePoolingArtificial intelligenceConvolutional neural networkScale (ratio)Pattern recognition (psychology)Object (grammar)Pyramid (geometry)Set (abstract data type)Computer visionCartographyMathematicsGeographyGeometryProgramming languageAdvanced Neural Network ApplicationsAdvanced Image and Video Retrieval TechniquesRobotics and Sensor-Based Localization