Expansion segmentation for visual collision detection and estimation

Abstract

Abstract-Collision detection and estimation from a monocular visual sensor is an important enabling technology for safe navigation of small or micro air vehicles in near earth flight. In this paper, we introduce a new approach called expansion segmentation, which simultaneously detects "collision danger regions" of significant positive divergence in inertial aided video, and estimates maximum likelihood time to collision (TTC) in a correspondenceless framework within the danger regions. This approach was motivated from a literature review which showed that existing approaches make strong assumptions about scene structure or camera motion, or pose collision detection without determining obstacle boundaries, both of which limit the operational envelope of a deployable system. Expansion segmentation is based on a new formulation of 6-DOF inertial aided TTC estimation, and a new derivation of a first order TTC uncertainty model due to subpixel quantization error and epipolar geometry uncertainty. Proof of concept results are shown in a custom designed urban flight simulator and on operational flight data from a small air vehicle.

First results in detecting and avoiding frontal obstacles from a monocular camera for micro unmanned aerial vehicles

“…There are many potential Computation is large. Cannot detect obstacle straight ahead [1], [2], [3], [4], [5], [6], [7], [8], [9] Monocular Cues Perspective Only useful in structured environments [10], [11] Relative Size Available for straight-on collisions [12], [13], [14] sensor modalities and in particular lidar based approaches have been shown to be able to sense obstacles reliably in [17], [18]. However, for size, weight, and power (SWAP) constraint vehicles cameras are the lightest sensor and given computing advances and the type of computation can be potentially very light.…”

“…However this approach depends on the texture in the environment and doesn't use the size expansion directly. Byrne et al [13] executed the expansion segmentation with inertial aid. However their demonstration is limited to simulation.…”

Spatio-temporal prediction of collision candidates for static and dynamic objects in monocular image sequences

“…In order to outline regions with similar attributes a clustering can be run on the flow field [26]. In this work regions of distorted vectors are clustered by a local search.…”

Monocular image-based time to collision and closest point of approach estimation

“…This scale ambiguity makes the decision about the possibility of mid-air collision (MAC) or near mid-air collision (NMAC) complicated. Image-based time-to-collision (TTC) estimation methods are published in [8], [9], [10]. Here, TTC is defined as the time until the intruder crosses the plane of camera focal point irrespective of the side distance.…”