Towards Pedestrian Target Detection with Optimized Mask R-CNN
Aiming at the problem of low pedestrian target detection accuracy, we propose a detection algorithm based on optimized Mask R-CNN which uses the latest research results of deep learning to improve the accuracy and speed of detection results. Due to the influence of illumination, posture, background,...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2020/6662603 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832554085225594880 |
|---|---|
| author | Dong-Hao Chen Yu-Dong Cao Jia Yan |
| author_facet | Dong-Hao Chen Yu-Dong Cao Jia Yan |
| author_sort | Dong-Hao Chen |
| collection | DOAJ |
| description | Aiming at the problem of low pedestrian target detection accuracy, we propose a detection algorithm based on optimized Mask R-CNN which uses the latest research results of deep learning to improve the accuracy and speed of detection results. Due to the influence of illumination, posture, background, and other factors on the human target in the natural scene image, the complexity of target information is high. SKNet is used to replace the part of the convolution module in the depth residual network model in order to extract features better so that the model can adaptively select the best convolution kernel during training. In addition, according to the statistical law, the length-width ratio of the anchor box is modified to make it more accord with the natural characteristics of the pedestrian target. Finally, a pedestrian target dataset is established by selecting suitable pedestrian images in the COCO dataset and expanded by adding noise and median filtering. The optimized algorithm is compared with the original algorithm and several other mainstream target detection algorithms on the dataset; the experimental results show that the detection accuracy and detection speed of the optimized algorithm are improved, and its detection accuracy is better than other mainstream target detection algorithms. |
| format | Article |
| id | doaj-art-6138b4a98d8c4d50876398119e5f0b18 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-6138b4a98d8c4d50876398119e5f0b182025-02-03T05:52:25ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/66626036662603Towards Pedestrian Target Detection with Optimized Mask R-CNNDong-Hao Chen0Yu-Dong Cao1Jia Yan2School of Electronics and Information Engineering, Liaoning University of Technology, Jinzhou, Liaoning 121001, ChinaSchool of Electronics and Information Engineering, Liaoning University of Technology, Jinzhou, Liaoning 121001, ChinaSchool of Electronics and Information Engineering, Liaoning University of Technology, Jinzhou, Liaoning 121001, ChinaAiming at the problem of low pedestrian target detection accuracy, we propose a detection algorithm based on optimized Mask R-CNN which uses the latest research results of deep learning to improve the accuracy and speed of detection results. Due to the influence of illumination, posture, background, and other factors on the human target in the natural scene image, the complexity of target information is high. SKNet is used to replace the part of the convolution module in the depth residual network model in order to extract features better so that the model can adaptively select the best convolution kernel during training. In addition, according to the statistical law, the length-width ratio of the anchor box is modified to make it more accord with the natural characteristics of the pedestrian target. Finally, a pedestrian target dataset is established by selecting suitable pedestrian images in the COCO dataset and expanded by adding noise and median filtering. The optimized algorithm is compared with the original algorithm and several other mainstream target detection algorithms on the dataset; the experimental results show that the detection accuracy and detection speed of the optimized algorithm are improved, and its detection accuracy is better than other mainstream target detection algorithms.http://dx.doi.org/10.1155/2020/6662603 |
| spellingShingle | Dong-Hao Chen Yu-Dong Cao Jia Yan Towards Pedestrian Target Detection with Optimized Mask R-CNN Complexity |
| title | Towards Pedestrian Target Detection with Optimized Mask R-CNN |
| title_full | Towards Pedestrian Target Detection with Optimized Mask R-CNN |
| title_fullStr | Towards Pedestrian Target Detection with Optimized Mask R-CNN |
| title_full_unstemmed | Towards Pedestrian Target Detection with Optimized Mask R-CNN |
| title_short | Towards Pedestrian Target Detection with Optimized Mask R-CNN |
| title_sort | towards pedestrian target detection with optimized mask r cnn |
| url | http://dx.doi.org/10.1155/2020/6662603 |
| work_keys_str_mv | AT donghaochen towardspedestriantargetdetectionwithoptimizedmaskrcnn AT yudongcao towardspedestriantargetdetectionwithoptimizedmaskrcnn AT jiayan towardspedestriantargetdetectionwithoptimizedmaskrcnn |