# Evolving Boxes for Fast Vehicle Detection

## TL;DR

This paper introduces Evolving Boxes, a fast deep learning framework for vehicle detection that refines object proposals using feature fusion, achieving high accuracy and real-time speed on traffic surveillance data.

## Contribution

The novel Evolving Boxes framework combines proposal generation and refinement with feature fusion, significantly improving detection accuracy and speed over existing methods.

## Key findings

- Achieved 9.5% higher mAP than Faster R-CNN on DETRAC benchmark.
- Reaches 9-13 FPS detection speed on a commercial GPU.
- Demonstrates effective proposal refinement using multi-level feature fusion.

## Abstract

We perform fast vehicle detection from traffic surveillance cameras. A novel deep learning framework, namely Evolving Boxes, is developed that proposes and refines the object boxes under different feature representations. Specifically, our framework is embedded with a light-weight proposal network to generate initial anchor boxes as well as to early discard unlikely regions; a fine-turning network produces detailed features for these candidate boxes. We show intriguingly that by applying different feature fusion techniques, the initial boxes can be refined for both localization and recognition. We evaluate our network on the recent DETRAC benchmark and obtain a significant improvement over the state-of-the-art Faster RCNN by 9.5% mAP. Further, our network achieves 9-13 FPS detection speed on a moderate commercial GPU.