Daxiang LI, Jiani XIN, Ying LIU. Position-sensitive Transformer aerial image object detection model[J]. Optics and Precision Engineering, 2024, 32(5): 727

Search by keywords or author
- Optics and Precision Engineering
- Vol. 32, Issue 5, 727 (2024)

Fig. 1. Schematic diagram of PS-TOD model

Fig. 2. Fusion scheme of PCE3DA cross layer feature map

Fig. 3. Flow chart of position channel embedding 3D attention

Fig. 4. Position sensitive self-attention mechanism

Fig. 5. Encoder-decoder structure

Fig. 6. Partial detection results of PS-TOD on VisDrone test set

Fig. 7. Comparison of small object detection result
|
Table 1. Ablation experiment results on VisDrone test set
|
Table 2. Experimental results for different attention mechanisms and using multi-scale features
|
Table 3. Experimental results of different relative position calculation methods
|
Table 4. Performance comparison of different algorithms on VisDrone test set
|
Table 5. Experimental results of different categories on VisDrone test set

Set citation alerts for the article
Please enter your email address