Face recognition performance evaluation has traditionally focused on one-to-one verification, popularized by the Labeled Faces in the Wild dataset [1] for imagery and the YouTubeFaces dataset [2] for videos. In contrast, the newly released IJB-A face recognition dataset [3] unifies evaluation of one-to-many face identification with one-to-one face verification over templates, or sets of imagery and videos for a subject. In this paper, we study the problem of template adaptation, a form of transfer learning to the set of media in a template. Extensive performance evaluations on IJB-A show a surprising result, that perhaps the simplest method of template adaptation, combining deep convolutional network features with template specific linear SVMs, outperforms the state-of-the-art by a wide margin. We study the effects of template size, negative set construction and classifier fusion on performance, then compare template adaptation to convolutional networks with metric learning, 2D and 3D alignment. Our unexpected conclusion is that these other methods, when combined with template adaptation, all achieve nearly the same top performance on IJB-A for template-based face verification and identification.

Abstract-Autonomous rendezvous and docking is necessary for planned space programs such as DARPA ASTRO, NASA MSR, ISS assembly and servicing, and other rendezvous and proximity operations. Estimation of the relative pose between the host platform and a resident space object is a critical ability. We present a model-based pose refinement algorithm, part of a suite of algorithms for vision-based relative pose estimation and tracking. Algorithms were tested in highfidelity simulation and stereo-vision hardware testbed environments. Testing indicated that in most cases, the modelbased pose refinement algorithm can handle initial attitude errors up to about 20 degrees, range errors exceeding 10% of range, and transverse errors up to about 2% of range. Preliminary point tests with real camera sequences of a 1/24 scale Magellan satellite model using a simple fixed-gain tracking filter showed potential tracking performance with mean errors of < 3 degrees and < 2% of range.

This paper presents the Visual Threat Awareness (VISTA) system for real time collision obstacle detection for an unmanned air vehicle (UAV). Computational stereo performance has progressed such that several commercial or open source implementations are available which operate at frame rate, but suffer from well known correspondence errors. We show that introducing a global segmentation step after commodity stereo can increase robustness and leverage existing stereo software. The global segmentation step is based on a graph structure appropriate for collision detection, human vision inspired foveation, perceptual organization and graph partitioning using the minimum s-t graph cut. This system has been prototyped using the Sarnoff Acadia I vision processor to enable processing of 640x480 resolution imagery at 5-10Hz operation on embedded avionics. We describe system theory, demonstrate segmentation results on scenes of increasing complexity, and show flight experiment results on Georgia Tech's GT-Max autonomous helicopter against real collision obstacles.

No 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.