Detection of Lower Body for AGV Based on SSD Algorithm with ResNet
Detection of human lower body provides an implementation idea for the automatic tracking and accurate relocation of automatic vehicles. Based on traditional SSD and ResNet, this paper proposes an improved detection algorithm R-SSD for human lower body detection, which utilizes ResNet50 instead of VG...
| Published in: | Sensors |
|---|---|
| Main Authors: | , , , , , |
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/5/2008 |
| _version_ | 1850099793972428800 |
|---|---|
| author | Xinbiao Gao Junhua Xu Chuan Luo Jun Zhou Panling Huang Jianxin Deng |
| author_facet | Xinbiao Gao Junhua Xu Chuan Luo Jun Zhou Panling Huang Jianxin Deng |
| author_sort | Xinbiao Gao |
| collection | DOAJ |
| container_title | Sensors |
| description | Detection of human lower body provides an implementation idea for the automatic tracking and accurate relocation of automatic vehicles. Based on traditional SSD and ResNet, this paper proposes an improved detection algorithm R-SSD for human lower body detection, which utilizes ResNet50 instead of VGG16 to improve the feature extraction level of the model. According to the application of acquisition equipment, the model input resolution is increased to 448 × 448 and the model detection range is expanded. Six feature maps of the updated resolution network are selected for detection and the lower body image dataset is clustered into five categories for aspect ratio, which are evenly distributed to each feature detection map. The experimental results show that the model R-SSD detection accuracy after training reaches 85.1% mAP. Compared with the original SSD, the detection accuracy is improved by 7% mAP. The detection confidence in practical application reaches more than 99%, which lays the foundation for subsequent tracking and relocation for automatic vehicles. |
| format | Article |
| id | doaj-art-e40dba7fd9674bc6a26835b5b8cf29dd |
| institution | Directory of Open Access Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| spelling | doaj-art-e40dba7fd9674bc6a26835b5b8cf29dd2025-08-20T00:05:21ZengMDPI AGSensors1424-82202022-03-01225200810.3390/s22052008Detection of Lower Body for AGV Based on SSD Algorithm with ResNetXinbiao Gao0Junhua Xu1Chuan Luo2Jun Zhou3Panling Huang4Jianxin Deng5School of Mechanical Engineering, Shandong University, Jinan 250061, ChinaSchool of Mechanical Engineering, Shandong University, Jinan 250061, ChinaSchool of Mechanical Engineering, Shandong University, Jinan 250061, ChinaSchool of Mechanical Engineering, Shandong University, Jinan 250061, ChinaSchool of Mechanical Engineering, Shandong University, Jinan 250061, ChinaSchool of Mechanical Engineering, Shandong University, Jinan 250061, ChinaDetection of human lower body provides an implementation idea for the automatic tracking and accurate relocation of automatic vehicles. Based on traditional SSD and ResNet, this paper proposes an improved detection algorithm R-SSD for human lower body detection, which utilizes ResNet50 instead of VGG16 to improve the feature extraction level of the model. According to the application of acquisition equipment, the model input resolution is increased to 448 × 448 and the model detection range is expanded. Six feature maps of the updated resolution network are selected for detection and the lower body image dataset is clustered into five categories for aspect ratio, which are evenly distributed to each feature detection map. The experimental results show that the model R-SSD detection accuracy after training reaches 85.1% mAP. Compared with the original SSD, the detection accuracy is improved by 7% mAP. The detection confidence in practical application reaches more than 99%, which lays the foundation for subsequent tracking and relocation for automatic vehicles.https://www.mdpi.com/1424-8220/22/5/2008object detectionSSDResNet |
| spellingShingle | Xinbiao Gao Junhua Xu Chuan Luo Jun Zhou Panling Huang Jianxin Deng Detection of Lower Body for AGV Based on SSD Algorithm with ResNet object detection SSD ResNet |
| title | Detection of Lower Body for AGV Based on SSD Algorithm with ResNet |
| title_full | Detection of Lower Body for AGV Based on SSD Algorithm with ResNet |
| title_fullStr | Detection of Lower Body for AGV Based on SSD Algorithm with ResNet |
| title_full_unstemmed | Detection of Lower Body for AGV Based on SSD Algorithm with ResNet |
| title_short | Detection of Lower Body for AGV Based on SSD Algorithm with ResNet |
| title_sort | detection of lower body for agv based on ssd algorithm with resnet |
| topic | object detection SSD ResNet |
| url | https://www.mdpi.com/1424-8220/22/5/2008 |
| work_keys_str_mv | AT xinbiaogao detectionoflowerbodyforagvbasedonssdalgorithmwithresnet AT junhuaxu detectionoflowerbodyforagvbasedonssdalgorithmwithresnet AT chuanluo detectionoflowerbodyforagvbasedonssdalgorithmwithresnet AT junzhou detectionoflowerbodyforagvbasedonssdalgorithmwithresnet AT panlinghuang detectionoflowerbodyforagvbasedonssdalgorithmwithresnet AT jianxindeng detectionoflowerbodyforagvbasedonssdalgorithmwithresnet |