Research on Deep Learning Automatic Vehicle Recognition Algorithm Based on RES-YOLO Model
With the introduction of concepts such as ubiquitous mapping, mapping-related technologies are gradually applied in autonomous driving and target recognition. There are many problems in vision measurement and remote sensing, such as difficulty in automatic vehicle discrimination, high missing rates...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/10/3783 |
| _version_ | 1797495685932646400 |
|---|---|
| author | Yanyi Li Jian Wang Jin Huang Yuping Li |
| author_facet | Yanyi Li Jian Wang Jin Huang Yuping Li |
| author_sort | Yanyi Li |
| collection | DOAJ |
| description | With the introduction of concepts such as ubiquitous mapping, mapping-related technologies are gradually applied in autonomous driving and target recognition. There are many problems in vision measurement and remote sensing, such as difficulty in automatic vehicle discrimination, high missing rates under multiple vehicle targets, and sensitivity to the external environment. This paper proposes an improved RES-YOLO detection algorithm to solve these problems and applies it to the automatic detection of vehicle targets. Specifically, this paper improves the detection effect of the traditional YOLO algorithm by selecting optimized feature networks and constructing adaptive loss functions. The BDD100K data set was used for training and verification. Additionally, the optimized YOLO deep learning vehicle detection model is obtained and compared with recent advanced target recognition algorithms. Experimental results show that the proposed algorithm can automatically identify multiple vehicle targets effectively and can significantly reduce missing and false rates, with the local optimal accuracy of up to 95% and the average accuracy above 86% under large data volume detection. The average accuracy of our algorithm is higher than all five other algorithms including the latest SSD and Faster-RCNN. In average accuracy, the RES-YOLO algorithm for small data volume and large data volume is 1.0% and 1.7% higher than the original YOLO. In addition, the training time is shortened by 7.3% compared with the original algorithm. The network is then tested with five types of local measured vehicle data sets and shows satisfactory recognition accuracy under different interference backgrounds. In short, the method in this paper can complete the task of vehicle target detection under different environmental interferences. |
| first_indexed | 2024-03-10T01:54:13Z |
| format | Article |
| id | doaj.art-a5509efd65fa4e11bd69de7208658dc2 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T01:54:13Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a5509efd65fa4e11bd69de7208658dc22023-11-23T13:01:03ZengMDPI AGSensors1424-82202022-05-012210378310.3390/s22103783Research on Deep Learning Automatic Vehicle Recognition Algorithm Based on RES-YOLO ModelYanyi Li0Jian Wang1Jin Huang2Yuping Li3College of Surveying and Geo-Informatics, Tongji Univesity, Shanghai 200092, ChinaCollege of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao 266590, ChinaOcean College, Zhejiang University, Zhoushan 316021, ChinaCollege of Surveying and Geo-Informatics, Tongji Univesity, Shanghai 200092, ChinaWith the introduction of concepts such as ubiquitous mapping, mapping-related technologies are gradually applied in autonomous driving and target recognition. There are many problems in vision measurement and remote sensing, such as difficulty in automatic vehicle discrimination, high missing rates under multiple vehicle targets, and sensitivity to the external environment. This paper proposes an improved RES-YOLO detection algorithm to solve these problems and applies it to the automatic detection of vehicle targets. Specifically, this paper improves the detection effect of the traditional YOLO algorithm by selecting optimized feature networks and constructing adaptive loss functions. The BDD100K data set was used for training and verification. Additionally, the optimized YOLO deep learning vehicle detection model is obtained and compared with recent advanced target recognition algorithms. Experimental results show that the proposed algorithm can automatically identify multiple vehicle targets effectively and can significantly reduce missing and false rates, with the local optimal accuracy of up to 95% and the average accuracy above 86% under large data volume detection. The average accuracy of our algorithm is higher than all five other algorithms including the latest SSD and Faster-RCNN. In average accuracy, the RES-YOLO algorithm for small data volume and large data volume is 1.0% and 1.7% higher than the original YOLO. In addition, the training time is shortened by 7.3% compared with the original algorithm. The network is then tested with five types of local measured vehicle data sets and shows satisfactory recognition accuracy under different interference backgrounds. In short, the method in this paper can complete the task of vehicle target detection under different environmental interferences.https://www.mdpi.com/1424-8220/22/10/3783deep learningautomatic drivingtarget recognitionadaptive loss functionYOLOvehicle detection model |
| spellingShingle | Yanyi Li Jian Wang Jin Huang Yuping Li Research on Deep Learning Automatic Vehicle Recognition Algorithm Based on RES-YOLO Model Sensors deep learning automatic driving target recognition adaptive loss function YOLO vehicle detection model |
| title | Research on Deep Learning Automatic Vehicle Recognition Algorithm Based on RES-YOLO Model |
| title_full | Research on Deep Learning Automatic Vehicle Recognition Algorithm Based on RES-YOLO Model |
| title_fullStr | Research on Deep Learning Automatic Vehicle Recognition Algorithm Based on RES-YOLO Model |
| title_full_unstemmed | Research on Deep Learning Automatic Vehicle Recognition Algorithm Based on RES-YOLO Model |
| title_short | Research on Deep Learning Automatic Vehicle Recognition Algorithm Based on RES-YOLO Model |
| title_sort | research on deep learning automatic vehicle recognition algorithm based on res yolo model |
| topic | deep learning automatic driving target recognition adaptive loss function YOLO vehicle detection model |
| url | https://www.mdpi.com/1424-8220/22/10/3783 |
| work_keys_str_mv | AT yanyili researchondeeplearningautomaticvehiclerecognitionalgorithmbasedonresyolomodel AT jianwang researchondeeplearningautomaticvehiclerecognitionalgorithmbasedonresyolomodel AT jinhuang researchondeeplearningautomaticvehiclerecognitionalgorithmbasedonresyolomodel AT yupingli researchondeeplearningautomaticvehiclerecognitionalgorithmbasedonresyolomodel |