A False Positive-Centric Framework for Object Detection Disambiguation

Abstract

Existing frameworks for classifying the fidelity for object detection tasks do not consider false positive likelihood and object uniqueness. Inspired by the Detection, Recognition, Identification (DRI) framework proposed by Johnson 1958, we propose a new modified framework, that defines three categories as Visible Anomaly, Identifiable Anomaly, and Unique Identifiable Anomaly (AIU) as determined by human interpretation of imagery or geophysical data. These categories are designed to better capture false positive rates and emphasizes the importance of identifying unique versus non-unique targets compared to the DRI Index. We then analyze visual, thermal and multispectral imagery collected over a seeded minefield and apply the AIU Index for the landmine detection use-case. We find that RGB imagery provided the most value per pixel achieving a 100% identifiable anomaly rate at 125 pixels on target, and the highest unique target classification compared to thermal and multispectral imaging for detection and identification of surface landmines and UXO. We also investigate how the AIU Index can be applied to machine learning for selection of training data and informing the required action to take after object detection bounding boxes are predicted. Overall, the anomaly, identifiable anomaly, unique identifiable anomaly index prescribes essential context for false-positive-sensitive or resolution-poor object detection tasks with applications in modality comparison, machine learning, and remote sensing data acquisition.

Keywords: Object detection, False positive, sensor fusion, remote sensing, Disambiguation, landmine detection