Gaze control system for tracking Quasi-1D high-speed moving object in complex background

Figures & data

Figure 1. Dual saccade mirror system (Okumura et al., 2011).

Figure 2. The structure of our system.

Figure 3. Left view of our system.

Figure 4. Top view of our system.

Figure 5. System operation flow chart.

Figure 6. Saccade mirror rotation angle and object movement displacement.

Figure 7. Cropping effect of two adjacent frames in the Bolt video.

Figure 8. Tracking results of the projectile video; (a) Sequence of four consecutive frames in the video, (b) Tracking results of traditional frame-difference method, (c) Tracking results of the method in this paper.

Table 1. Speed comparison of target tracking methods.

Tracker	FPS
D3S (Lukezic et al., 2020)	25
Ocean (Zhang & Peng, 2020)	58
AFAT (Xu et al., 2020)	70.5
AFOD (Y. Chen et al., 2020)	149
Frame-difference method	915
Frame-difference method based on image cropping	749

Table 2. Experimental-related equipment and parameters.

High-speed camera	Moldel: Revealer M220
	Maximum resolution: $1920\times 1080$
	Shooting resolution: $448\times 340$
	Shooting rate: 2000 fps
	Pixel size: 10 pm
Saccade mirror	Lens size: $16\mathrm{m}\mathrm{m}\times 18\mathrm{m}\mathrm{m}$
	Small angle step response times: 0.12 ms
	Maximum scanning angle: $\pm {40}^{\circ }$(optical angle)
	Linearity: 99.0$\mathrm{\%}$
Experimental environment	Frame-difference threshold: 40pixel
	f: 50 mm
	L: 988 mm
	$\text{β}:{23.1}^{\circ }$

Figure 9. Experimental results; (a) Four consecutive images taken by the camera, (b) Tracking results of traditional frame-difference method, (c) Tracking results of the method in this paper.

Figure 10. Launcher.

Figure 11. Gaze control for tracking a soft toy bullet uses our system.

Okumura, K., Oku, H., & Ishikawa, M. (2011). High-speed gaze controller for millisecond-order pan/tilt camera. In IEEE International Conference on Robotics and Automation (pp. 6186–6191). https://doi.org/10.1109/ICRA.2011.5980080.

 Google Scholar

Lukezic, A., Matas, J., & Kristan, M. (2020). D3S–a discriminative single shot segmentation tracker. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 7133–7142). https://doi.org/10.1109/CVPR42600.2020.00716.

 Google Scholar

Zhang, Z., & Peng, H. (2020). Object-aware anchor-free tracking. In Proceedings of the 16th European Conference on Computer Vision (ECCV 2020) (Vol. 12366, pp. 771–787). https://doi.org/10.1007/978–3-030–58589-146.

 Google Scholar

Xu, T., Feng, Z. H., Wu, X. J., & Kittler, J. (2020). AFAT: Adaptive failure-aware tracker for robust visual object tracking. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1–17).

 Google Scholar

Chen, Y., Xu, J., Yu, J., Wang, Q., Yoo, B., & Han, J. J. (2020). AFOD: Adaptive focused discriminative segmentation tracker. Proceedings of the 16th European Conference on Computer Vision (ECCV 2020), 12539, 666–682. https://doi.org/10.1007/978–3-030–68238-544.

 Google Scholar

Data availability statement

Data sharing is not applicable to this article as no new data were created or analysed in this study.