Fusion of an Ensemble of Augmented Image Detectors for Robust Object Detection

TL;DR

This paper introduces a fusion approach combining multiple augmented image detectors with dynamic agreement analysis, significantly improving object detection accuracy and robustness in ADAS applications.

Contribution

It presents a novel fusion method based on dynamic agreement analysis and an online augmentation strategy for enhanced object detection.

Findings

Augmented and fused detectors outperform individual methods in accuracy.

Fusion reduces outlier influences and improves robustness.

Approach effective in cone, pedestrian, and box detection for ADAS.

Abstract

A significant challenge in object detection is accurate identification of an object's position in image space, whereas one algorithm with one set of parameters is usually not enough, and the fusion of multiple algorithms and/or parameters can lead to more robust results. Herein, a new computational intelligence fusion approach based on the dynamic analysis of agreement among object detection outputs is proposed. Furthermore, we propose an online versus just in training image augmentation strategy. Experiments comparing the results both with and without fusion are presented. We demonstrate that the augmented and fused combination results are the best, with respect to higher accuracy rates and reduction of outlier influences. The approach is demonstrated in the context of cone, pedestrian and box detection for Advanced Driver Assistance Systems (ADAS) applications.