UAV-Based Human Body Detector Selection and Fusion for Geolocated Saliency Map Generation

TL;DR

This paper presents a system for UAV-based detection and geolocation of objects, combining detector selection, resource-aware execution, and fusion of detection results to generate accurate saliency maps in real-time.

Contribution

It introduces an offline evaluation framework for detector selection, an automatic online detector allocation method, and a novel fusion approach for geolocated saliency map generation.

Findings

Effective detector selection based on system constraints.

Successful fusion of multi-UAV detection results.

Validated approach through simulated and real flight experiments.

Abstract

The problem of reliably detecting and geolocating objects of different classes in soft real-time is essential in many application areas, such as Search and Rescue performed using Unmanned Aerial Vehicles (UAVs). This research addresses the complementary problems of system contextual vision-based detector selection, allocation, and execution, in addition to the fusion of detection results from teams of UAVs for the purpose of accurately and reliably geolocating objects of interest in a timely manner. In an offline step, an application-independent evaluation of vision-based detectors from a system perspective is first performed. Based on this evaluation, the most appropriate algorithms for online object detection for each platform are selected automatically before a mission, taking into account a number of practical system considerations, such as the available communication links, video compression used, and the available computational resources. The detection results are fused using a method for building maps of salient locations which takes advantage of a novel sensor model for vision-based detections for both positive and negative observations. A number of simulated and real flight experiments are also presented, validating the proposed method.