From Superpixel to Human Shape Modelling for Carried Object Detection

TL;DR

This paper introduces a novel multi-scale superpixel-based method for detecting carried objects in single video frames, combining feature matching and probability maps to accurately identify and shape carried objects.

Contribution

The approach uniquely integrates multi-scale superpixel segmentation with feature matching against a learned codebook for improved carried object detection.

Findings

Method performs competitively with state-of-the-art techniques.

Effective in challenging datasets with complex scenes.

High accuracy in identifying and shaping carried objects.

Abstract

Detecting carried objects is one of the requirements for developing systems to reason about activities involving people and objects. We present an approach to detect carried objects from a single video frame with a novel method that incorporates features from multiple scales. Initially, a foreground mask in a video frame is segmented into multi-scale superpixels. Then the human-like regions in the segmented area are identified by matching a set of extracted features from superpixels against learned features in a codebook. A carried object probability map is generated using the complement of the matching probabilities of superpixels to human-like regions and background information. A group of superpixels with high carried object probability and strong edge support is then merged to obtain the shape of the carried object. We applied our method to two challenging datasets, and results show that our method is competitive with or better than the state-of-the-art.