We present a novel method for vehicle detection and classification in aerial imagery. First, change detection analyzes a pair of mutually aligned images captured at the same location but at different time instants to generate vehicle proposals. Next, a trained Convolutional Neural Network (CNN) classifier is applied to (1) determine if a proposal truly contains a vehicle, and (2) classify any vehicle present into major categories. Experimental results using infrared (IR) data demonstrate the efficacy of our method: vehicle detection rate is over 99%; light-duty vehicles (e.g. sedan) are classified with 89% accuracy, medium-duty vehicles (e.g., van and pickup) with 79% and heavy-duty vehicles (e.g., trucks and buses) with 73% accuracies. The classification performance difference among different vehicle types is attributed to the size of training samples available in each category. Our system can process data at video rate making it feasible for real-time traffic monitoring.

Change detection in aerial imagery is challenging due to the effects of platform movements, atmospheric degradation and unpredictable photometric or thermal variations of the scene. We introduce an aerial change detection system built around multiple change detectors, each exploiting a different feature set, and fusion of their output in order to overcome the challenges. A supervised classifier screens the fused results for false detections. In particular, we have investigated three change detectors: Histogram of Oriented Gradients (HOG), Clustering-Based Anomaly Detection (CBCD), and Local Binary Similarity Pattern (LBSP). A set of change regions (blobs) are retained following fusion. Next, a set of features are extracted from each blob and fed into an AdaBoost classifier for true change acceptance test. Ours is a multithreaded system performing change detection in real time. Test results on a variety of EO and IR imagery demonstrate the efficacy our system in real-world applications.

This paper compares the performances of the binocular cues of stereo and vergence, and the monocular cue of focus for range estimation using an active vision system. The performance of each cue is characterized in terms of sensitivity to errors in the imaging parameters. The effects of random, quantization errors are expressed in terms of the standard deviation of the resulting depth error. The effect of systematic, calibration errors on estimation using each cue is also studied. Performance characterization of each cue is utilized to evaluate the relative performance of the cues. Also discussed, based on such characterization, are ways to select a cue taking into account the computational and reliability aspects of the corresponding estimation process.

Recognition of aircraft in complex, perspective aerial imagery has to be accomplished in presence of clutter, occlusion, shadow, and various forms of image degradation. This paper presents a system for aircraft recognition under real-world conditions that is based on the use of a hierarchical database of object models. The particular approach involves three key processes: (a) The qualitative object recognition process performs model-based symbolic feature extraction and generic object recognition; (b) The refocused matching and evaluation process refines the extracted features for more specific classification with input from (a); and (c) The primitive feature extraction process regulates the extracted features based on their saliency and interacts with (a) and (b). Experimental results showing the qualitative recognition of aircraft in perspective, aerial images are presented.>

The performances of the binocular cues of stereo, vergence, and the monocular cue of focus for range estimation using an active vision system are compared. The performance of each cue is characterized by its sensitivity to errors in the imaging parameters. The effect of random quantization errors is expressed in terms of the standard derivation of the resulting depth error. The effect of systematic calibration errors on estimation using each cue is studied. Performance characterization of each cue is shown to be useful for active control of the imaging parameters to improve the accuracy of the estimated range. Methods to integrate the use of the cues in order to overcome their individual limitations are discussed.>

Any mobile robotic task requires information about the environment so that an appropriate physical action may be taken. A sensory action allows the robot to collect this necessary information. This paper is concerned with developing a timeoptimal sensing strategy. We propose to relate the time of a particular action to its usefulness in the robotic task as the basis of the strategy. The specific approach requires dynamic models of sensors, kinematic models of robots, error models of the sensory and kinematic processes, and a metric to compute the distance between physical states of the robot. The sensing strategy is described as the extremization of a payoff function defined in terms of the sensory action time and the localization accuracy of the current physical state of the robot with respect to its goal state using sensory information.

Airborne vehicles such as rotorcraft must avoid obstacles such as antennas, towers, poles, fences, tree branches, and wires strung across the flight path. The paper analyzes the requirements of an obstacle detection system for rotorcrafts in low-altitude Nap-of-the-Earth flight based on various rotorcraft motion constraints. It argues that an automated obstacle detection system for the rotorcraft scenario should include both passive and active sensors. Consequently, it introduces a maximally passive system which involves the use of passive sensors (TV, FLIR) as well as the selective use of an active (laser) sensor. The passive component is concerned with estimating range using optical flow-based motion analysis and binocular stereo in conjunction with inertial navigation system information. Experimental results obtained using land vehicle data illustrate the particular approach to motion analysis.>

Consideration is given to the problem of surface reconstruction from stereo images for large scenes having large depth ranges where it is necessary to aim cameras in different directions and to fixate at different objects. The authors concentrate on the selection of new fixation points from among the nonfixated, low resolution scene parts, and subsequent processing for surface reconstruction. The coarse stereo estimates in the vicinity of the new fixation point are refined as the images of the new fixation point gradually deblur during the process of refixation and are subsequently used to analyze the fixated parts of the scene.>

A multiprocessor architecture called NETRA is discussed. It is highly reconfigurable and does not involve the use of complex interconnection schemes. The topology of this multiprocessor is recursively defined and is therefore easily scalable from small to large systems. It has a tree-type hierarchical architecture featuring leaf nodes that consist of a cluster of small but powerful processors connected via a programmable crossbar with selective broadcast capability. The architecture is simulated on a hypercube multiprocessor and the performance of one processor cluster is evaluated for stereo-vision tasks. The particular stereo algorithm selected for implementation requires computation of the two-dimensional fast Fourier transform (2-D FFT), template matching, histogram computation, and least-squares surface fitting. Static partitioning of data is used for the data-independent tasks such as 2-D FFT and dynamic scheduling, and load balancing is used for the data-dependent tasks of feature matching and disambiguation.>