Human Body Parts Detection using Improved YOLOv5 with Multi-Layer Attention Network (MLA-NET)
02Indian Institute of Technology, Bhilai2023 - Present
Scroll to explore
DesignedanenhancedYOLOv5-baseddetectionframeworkintegratedwithaMulti-LayerAttentionNetwork(MLA-NET)foraccuratehumanbodypartdetectionindisasterrescuescenarios.
Developed a multi-layer attention module combining channel attention and pixel attention to improve feature refinement.
Automated ground-truth generation using OpenPose-based body joint estimation.
Enhanced low-resolution disaster footage using Real-ESRGAN super-resolution models.
Implemented frame extraction pipelines for video-to-image dataset creation.
Achieved improved robustness in detecting partially occluded or irregularly posed victims.
Work in detail
01 // Exhibit
ATTENTION ARCHITECTURE
Channel + Pixel attention integration improving detection accuracy in complex rescue environments.
A closer look
Next in the archive
