Fig. 1. Process of infrared video image stabilization algorithm based on joint camera path

Fig. 2. Motion model based on grid mapping. (a) Correspondence between two frames of image grids; (b) Shape retention constraints

Fig. 3. Schematic diagram of the joint camera path solution process. (a) Path iteration of the grid; (b) Relationship among the initial camera path C(t), smooth path P(t), and compensation path B(t)

Fig. 4. Comparison of image stability results in the case of abundant feature points and few feature points. (a) Rich feature point set；(b) Less feature point set

Fig. 5. Image corresponds to the joint camera path and the optimized path. (a) Corresponding grids between image frames; (b) Results before and after path optimization: the left side is the (1, 1) grid, and the right side is the (1, 1) grid

Fig. 6. Smoothing results before and after adding the second restraint. (a) Original image; (b) Without the second restraint; (c) Result in this paper

Fig. 7. Pseudo code of the algorithm in this paper

Fig. 8. Comparison of image stability results between single path and joint path. (a) Path optimization results; (b) Image after image stabilization: the left side is the single path, and the right side is the joint path

Fig. 9. Comparison of results of various image stabilization algorithms under the Driving type video. (a) Original image; (b) L1 algorithm; (c) AE system; (d) Zhu Juanjuan's electronic image stabilization algorithm; (e) Proposed algorithm

Fig. 10. Comparison of results of various image stabilization algorithms under the Zooming type video. (a) Original image; (b) L1 algorithm (c) AE system; (d) Zhu Juanjuan's electronic image stabilization algorithm; (e) Proposed algorithm

Fig. 11. Quantitative evaluation results of several image stabilization algorithms under seven sets of videos. (a) Simple; (b) Rotation; (c) Zooming; (d) Parallax; (e) Driving; (f) Crowd; (g) Running