Detangling People: Individuating Multiple Close People and Their Body Parts via Region Assembly

TL;DR

This paper introduces a novel region assembly approach to accurately separate and identify multiple closely situated people and their body parts in complex images, improving robustness over existing methods.

Contribution

It formulates person detangling as a region assembly problem with a novel optimization and Lagrangian relaxation, enabling pixel-level body part and individual assignment in crowded scenes.

Findings

Outperforms existing detection and segmentation methods on challenging datasets.

Robustly handles occlusion, clutter, and complex poses.

Enhances proxemics recognition accuracy in crowded images.

Abstract

Today's person detection methods work best when people are in common upright poses and appear reasonably well spaced out in the image. However, in many real images, that's not what people do. People often appear quite close to each other, e.g., with limbs linked or heads touching, and their poses are often not pedestrian-like. We propose an approach to detangle people in multi-person images. We formulate the task as a region assembly problem. Starting from a large set of overlapping regions from body part semantic segmentation and generic object proposals, our optimization approach reassembles those pieces together into multiple person instances. It enforces that the composed body part regions of each person instance obey constraints on relative sizes, mutual spatial relationships, foreground coverage, and exclusive label assignments when overlapping. Since optimal region assembly is a challenging combinatorial problem, we present a Lagrangian relaxation method to accelerate the lower bound estimation, thereby enabling a fast branch and bound solution for the global optimum. As output, our method produces a pixel-level map indicating both 1) the body part labels (arm, leg, torso, and head), and 2) which parts belong to which individual person. Our results on three challenging datasets show our method is robust to clutter, occlusion, and complex poses. It outperforms a variety of competing methods, including existing detector CRF methods and region CNN approaches. In addition, we demonstrate its impact on a proxemics recognition task, which demands a precise representation of "whose body part is where" in crowded images.