Author Affiliations
1School of Management Engineering, Jilin Communications Polytechnic, Changchun, Jilin 130012, China2School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, Jilin 130022, Chinashow less
Fig. 1. Structure of SSD300 network
Fig. 2. Structure of two-channel network
Fig. 3. Improved two-channel SSD network model based on feature fusion
Fig. 4. Partial depth images. (a) Image 1; (b) image 2; (c) image 3
Fig. 5. Color images and depth images under different operations. (a) Original images; (b) 180 ° rotation; (c) x-axis reversal; (d) y-axis reversal
Fig. 6. Training loss and accuracy curves. (a) Training loss curve; (b) accuracy curve
Fig. 7. Relationship between precision and recall of different networks
Fig. 8. Detection results of SSD network and two-channel SSD network. (a) Original images; (b)SSD network; (c) two-channel SSD network
Fig. 9. Detection results of SSD network and improved SSD network with multi-scale feature fusion. (a) Original images; (b) SSD network; (c) two-channel SSD network
Fig. 10. Detection results of each algorithm under different illumination variation conditions. (a) SSD algorithm; (b) DSSD algorithm; (c) improved algorithm
Fig. 11. Detection results of each algorithm under different occlusion conditions. (a) SSD algorithm; (b) DSSD algorithm; (c) improved algorithm
Parameter | MDConv 4_3_fusion | FC 7_fusion | Conv 8_2_fusion |
---|
Feature map size/(pixel×pixel) | 38×38 | 19×19 | 10×10 | Number of default boxes | 4 | 6 | 3 | ar | {1,1,2,1/2} | {1,1,2,1/2,3,1/3} | {1,2,1/2} | Small side length | 30 | 60 | 111 | Large side length | 60 | 111 | - |
|
Table 1. Size of default box for each layer
Network | mAP/% | FPS |
---|
Simplified SSD network | 83.70 | 33 | SSD network | 84.90 | 29 |
|
Table 2. Average accuracy and speed of target detection in different prior frame networks
Fusion mode | Weight ratio | RGB image | Depth image | Two-channel SSD |
---|
Concat | | 83.70 | 82.61 | 89.86 | Eltwise | 0.7∶0.3 | 93.59 | 0.5∶0.5 | 91.94 | 0.3∶0.7 | 87.46 |
|
Table 3. Average detection accuracy of two-channel SSD network unit: %
Parameter | SSD | DSSD | Multi-scale SSD |
---|
mAP | 83.70 | 88.43 | 91.47 |
|
Table 4. Average detection accuracy of multi-scale feature fusion network unit: %
Parameter | SSD | RGB-D+YOLOv2 | RGB-D+Faster-RCNN | Ref. [18] | Ref. [19] | Ref. [25] | Proposed model |
---|
mAP | 84.90 | 92.95 | 93.14 | 92.01 | 90.78 | 95.47 | 97.80 |
|
Table 5. Average detection accuracy of different models unit: %