Advanced Perspective on Human Detection system with Hybrid Feature Set

Detecting and discriminating humans in video frames for surveillance applications is a demanding task. Identifying highlighting by eliminating shadows from the vital prudence motive. In this paper, three-step procedure proposed, which includes motion detection background subtraction live frames, morphological gradient-based shadow removal, human Hybrid Feature Set (HFS), comprises Histogram Oriented Gradient (HOG) Local Binary Pattern (LBP) with adaptive Neuro-Fuzzy inference system. The first step incorporates static dynamic subtraction. second to remove using gradient horizontal directional mask. third near-field, mid-field, far-field an results obtained various performed experimental analysis demonstrates diverse parametrical measures, outperforms comparatively when benchmark databases real-time were used.