Research on 24-Hour Dense Crowd Counting and Object Detection System Based on Multimodal Image Optimization Feature Fusion

Table 2

Comparison of the different state-of-the-art methods on MICC dataset.

Model	MAE	MSE
RetinaNet [59]	1.641	2.554
DetNet [60]	1.541	2.382
Idrees et al. [61]	1.396	2.642
MCNN [62]	1.5	2.259
CSRNet [63]	1.359	2.125
Cascaded-DCNet [64]	0.836	1.031
MCNN-adaptive [61]	1.489	2.114
CSRNet-adaptive [61]	1.343	2.007
RDNet [65]	1.38	2.551
Ours (RGBD-Net-adaptive)	1.025	1.521