Author Affiliations
1Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China2Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China3University of Chinese Academy of Sciences, Beijing 100049, China4Key Laboratory of Opto-electronic Information Processing, Chinese Academy of Sciences, Shenyang 110016, China5The Key Lab of Image Understanding and Computer Vision, Liaoning Province, Shenyang 110016, Chinashow less
Fig. 1. Algorithm flow chart
Fig. 2. Response map based on spectral residual visual saliency. (a) Initialized target map; (b) Spectral residual response map; (c) Three-dimensional map of spectral residual response
Fig. 3. Illustration of image texture detail. (a) Binary image of Canny edge; (b) Gradient direction amplitude map; (c) Edge direction dispersion map; (d) Three-dimensional map of edge direction dispersion
Fig. 4. Illustration of joint suitable-matching confidence map based on multi-feature fusion. (a) Joint suitable-matching confidence map; (b) Three- dimensional map of joint suitable-matching confidence
Fig. 5. Result of automatic parts selection
Fig. 6. Experimental results of proposed method on OTB100 dataset. (a) Results of automatic parts selection on sequence Carscale; (b) Results of automatic parts selection on sequence Dancer2
Fig. 6. [in Chinese]
Fig. 7. Experimental results of proposed method on FLIR Thermal dataset. (a) Results of automatic parts selection on the infrared target #1; (b) Results of automatic parts selection on infrared target #2
Fig. 8. Experimental results of proposed method on private infrared sequences. (a) Results of automatic parts selection on the private infrared sequence #1; (b) Results of automatic parts selection on the private infrared sequence #2
Fig. 9. Distance precision and overlap success rate curves of different algorithms under deformation and occlusion attribute. (a) Distance precision curve of deformation attribute; (b) Overlap success rate curve of deformation attribute; (c) Distance precision curve of occlusion attribute; (d) Overlap success rate curve of deformation attribute
Fig. 10. Frame-by-frame center location errors of parts from proposed in the paper and manual selection in different sequences
Aspect ratio | Number of parts | Width of parts (
${p_w}$![]() )
| Height of parts (
${p_h}$![]() )
| Horizontal margin (
${M_x}$![]() )
| Vertical margin (
${M_y}$![]() )
| $AR \leqslant \dfrac{2}{3}$ | 3 | $\left\lceil {0.8W} \right\rceil $ | $\left\lceil {0.8 \times \dfrac{H}{3} } \right\rceil$ | $\left\lceil {0.05 \times W} \right\rceil$ | $\left\lceil {0.05 \times H} \right\rceil$ | $\dfrac{2}{3} < AR \leqslant \dfrac{3}{2}$ | 4 | $\left\lceil {0.8\dfrac{W}{2} } \right\rceil$ | $\left\lceil {0.8 \times \dfrac{H}{2} } \right\rceil$ | $AR > \dfrac{3}{2}$ | 3 | $\left\lceil {0.8 \times \dfrac{W}{3} } \right\rceil$ | $\left\lceil {0.8 \times H} \right\rceil$ |
|
Table 1. Principle of adaptive selection of parts
Sequence | Proposed | Manual selection | Sylvester | 2.9124 | 4.0036 | Gym | 10.888 | 15.816 | Dancer2 | 7.5905 | 8.4727 |
|
Table 2. Mean center location error in different sequences