MISD-SLAM: Multimodal Semantic SLAM for Dynamic Environments

Figure 7

Trajectory comparison of original PL-SVO [37] and processed PL-SVO in dynamic sequences. Sitting series is in low-dynamic, and walking series is in high-dynamic. The green line is the trajectory of original PL-SVO, the blue line is the trajectory of processed PL-SVO, and the black dotted line is the ground truth.

(a) sitting_static

(b) walking_rpy

(c) walking_halfsphere

(d) walking_xyz