Fig. 1. Structural diagram of channel fusion residual block (RCFBlock)

Fig. 2. Structural diagram of MCFUBlock

Fig. 3. Structural diagram of expanded spatial attention module guided by edge information (EGSAM)

Fig. 4. Structure diagram of complete EGMFNet

Fig. 5. Structure diagram of U-block with residual connection

Fig. 6. EGMFNet prediction annotation rendering

Fig. 7. EGMFNet prediction annotation rendering

Table 1. Comparison of the experimental results

Table 2. Parameter quantity and real-time evaluation of EGFMNet

Table 3. Ablation experimental results. GA is the basic network trained with BCE Loss, GB is the basic network trained with mixed loss, GC is the complete network with three-stage EGSAM module and trained with BCE Loss, and GD is the complete network with three-stage EGSAM module and trained with mixed loss

Table 4. RCFBlock stack quantity verification experiment

Table 5. Verify the experimental results at EGSAM module level

Table 6. EGSAM fusion coefficient setting experiment