Simultaneous x, y Pixel Estimation and Feature Extraction for Multiple Small Objects in a Scene: A Description of the ALIEN Network
This addresses the challenge of efficient multi-object detection for applications like autonomous driving or surveillance, though it appears incremental as it builds on existing deep learning methods.
The paper tackles the problem of detecting multiple small objects in a scene by simultaneously estimating their pixel locations and feature sets, such as orientation and color, in a single forward pass, achieving fast and efficient implementation as demonstrated in vehicle detection.
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.