End-to-end people detection in crowded scenes

TL;DR

This paper introduces an end-to-end model for detecting people in crowded scenes that directly outputs detection sets without post-processing, utilizing a recurrent LSTM and a novel set-based loss function.

Contribution

It presents a novel end-to-end detection framework that eliminates the need for post-processing steps like non-maximum suppression, improving detection in crowded scenes.

Findings

Effective detection in crowded scenes demonstrated

Eliminates need for non-maximum suppression

Uses a recurrent LSTM with set-based loss

Abstract

Current people detectors operate either by scanning an image in a sliding window fashion or by classifying a discrete set of proposals. We propose a model that is based on decoding an image into a set of people detections. Our system takes an image as input and directly outputs a set of distinct detection hypotheses. Because we generate predictions jointly, common post-processing steps such as non-maximum suppression are unnecessary. We use a recurrent LSTM layer for sequence generation and train our model end-to-end with a new loss function that operates on sets of detections. We demonstrate the effectiveness of our approach on the challenging task of detecting people in crowded scenes.