Simultaneous x, y Pixel Estimation and Feature Extraction for Multiple Small Objects in a Scene: A Description of the ALIEN Network

TL;DR

The paper introduces the ALIEN deep-learning network capable of detecting numerous small objects in a scene while simultaneously estimating their pixel locations and features in a single, efficient forward pass.

Contribution

It presents a novel network architecture that combines object detection and feature extraction for small objects in a single, fast inference step.

Findings

Effective detection of hundreds to thousands of small objects

Simultaneous estimation of object locations and features

High efficiency in processing multiple objects

Abstract

We present a deep-learning network that detects multiple small objects (hundreds to thousands) in a scene while simultaneously estimating their x,y pixel locations together with a characteristic feature-set (for instance, target orientation and color). All estimations are performed in a single, forward pass which makes implementing the network fast and efficient. In this paper, we describe the architecture of our network --- nicknamed ALIEN --- and detail its performance when applied to vehicle detection.