Outdoor Imagery Research Articles

BirdCollect: A Comprehensive Benchmark for Analyzing Dense Bird Flock Attributes

Automatic recognition of bird behavior from long-term, un controlled outdoor imagery can contribute to conservation efforts by enabling large-scale monitoring of bird populations. Current techniques in AI-based wildlife monitoring have focused on short-term tracking and monitoring birds individually rather than in species-rich flocks. We present Bird-Collect, a comprehensive benchmark dataset for monitoring dense bird flock attributes. It includes a unique collection of more than 6,000 high-resolution images of Demoiselle Cranes (Anthropoides virgo) feeding and nesting in the vicinity of Khichan region of Rajasthan. Particularly, each image contains an average of 190 individual birds, illustrating the complex dynamics of densely populated bird flocks on a scale that has not previously been studied. In addition, a total of 433 distinct pictures captured at Keoladeo National Park, Bharatpur provide a comprehensive representation of 34 distinct bird species belonging to various taxonomic groups. These images offer details into the diversity and the behaviour of birds in vital natural ecosystem along the migratory flyways. Additionally, we provide a set of 2,500 point-annotated samples which serve as ground truth for benchmarking various computer vision tasks like crowd counting, density estimation, segmentation, and species classification. The benchmark performance for these tasks highlight the need for tailored approaches for specific wildlife applications, which include varied conditions including views, illumination, and resolutions. With around 46.2 GBs in size encompassing data collected from two distinct nesting ground sets, it is the largest birds dataset containing detailed annotations, showcasing a substantial leap in bird research possibilities. We intend to publicly release the dataset to the research community. The database is available at: https://iab-rubric.org/resources/wildlife-dataset/birdcollect

Sky pixel detection in outdoor imagery using an adaptive algorithm and machine learning

Computer vision techniques enable automated detection of sky pixels in outdoor imagery. In urban climate, sky detection is an important first step in gathering information about urban morphology and sky view factors. However, obtaining accurate results remains challenging and becomes even more complex using imagery captured under a variety of lighting and weather conditions.To address this problem, we present a new sky pixel detection system demonstrated to produce accurate results using a wide range of outdoor imagery types. Images are processed using a selection of mean-shift segmentation, K-means clustering, and Sobel filters to mark sky pixels in the scene. The algorithm for a specific image is chosen by a convolutional neural network, trained with 25,000 images from the Skyfinder data set, reaching 82% accuracy for the top three classes. This selection step allows the sky marking to follow an adaptive process and to use different techniques and parameters to best suit a particular image. An evaluation of fourteen different techniques and parameter sets shows that no single technique can perform with high accuracy across varied Skyfinder and Google Street View data sets. However, by using our adaptive process, large increases in accuracy are observed. The resulting system is shown to perform better than other published techniques.

An analysis of altitude, citizen science and a convolutional neural network feedback loop on object detection in Unmanned Aerial Systems

Using automated processes to detect wildlife in uncontrolled outdoor imagery in the field of wildlife ecology is a challenging task. In imagery provided by Unmanned Aerial Systems (UAS), this is especially true where individuals are small and visually similar to background substrates. To address these challenges, this work presents an automated feedback loop which can operate on large scale imagery, such as UAS generated orthomosaics, to train convolutional neural networks (CNNs) with extremely unbalanced class sizes. This feedback loop was used to help train CNNs using imagery classified by both expert biologists and citizen scientists at the Wildlife@home project. Utilizing the feedback loop dramatically reduced population count error rates from previously published work: from +150% to −3.93% on citizen scientist training data and +88% to +5.24% on expert training data. The system developed was then utilized to investigate the effect of altitude on CNN predictions. The training dataset was split into three subsets depending on the altitude of the imagery (75 m, 100 m and 120 m). While the lowest altitude was shown to provide the best predictions of the three (+11.46%), the aggregate data set still provided the best results (−3.93%) indicating that there is greater benefit to be gained from a large data set at this scale, and there is potential benefit to having training data from multiple altitudes. This article is an extended version of “Detecting Wildlife in Unmanned Aerial Systems Imagery using Convolutional Neural Networks Trained with an Automated Feedback Loop” published in the proceedings of the 18th International Conference of Computational Science (ICCS 2018) [1].

First results from a dual photoelastic-modulator-based polarimetric camera

We report on the construction and calibration of a dual photoelastic-modulator (PEM)-based polarimetric camera operating at 660?nm. This camera is our first prototype for a multispectral system being developed for airborne and spaceborne remote sensing of atmospheric aerosols. The camera includes a dual-PEM assembly integrated into a three-element, low-polarization reflective telescope and provides both intensity and polarization imaging. A miniaturized focal-plane assembly consisting of spectral filters and patterned wire-grid polarizers provides wavelength and polarimetric selection. A custom push-broom detector array with specialized signal acquisition, readout, and processing electronics captures the radiometric and polarimetric information. Focal-plane polarizers at orientations of 0 degrees and -45 degrees yield the normalized Stokes parameters q=Q/I and u=U/I respectively, which are then coregistered to obtain degree of linear polarization (DOLP) and angle of linear polarization. Laboratory test data, calibration results, and outdoor imagery acquired with the camera are presented. The results show that, over a wide range of DOLP, our challenging objective of uncertainty within +/-0.005 has been achieved.

Comparison of diurnal contrast changes for millimeter-wave and infrared imagery

Far-infrared outdoor imagery has a lower contrast in the morning/afternoon relative to the highest contrast, which is observed at 14:00. Millimeter-wave (mmW) imagery can also follow this pattern. However, in this paper, we show that the opposite can occur for mmW imagery, wherein a higher contrast can occur in the morning/afternoon and lower contrast at 14:00. To this end, we show that a wood and rubber sample are observed to have a difference in mmW radiometric temperature of 17 degrees C at 9:00 and a difference of only 7 degrees C at 14:00. Details of our observations are presented.

Continuous Stereo Self-Calibration by Camera Parameter Tracking

This paper presents a consistent framework for continuous stereo self-calibration. Based on a practical analysis of the sensitivity of stereo reconstruction to camera calibration uncertainties, we identify important parameters for self-calibration. We evaluate different geometric constraints for estimation and tracking of these parameters: bundle adjustment with reduced structure representation relating corresponding points in image sequences, the epipolar constraint between stereo image pairs, and trilinear constraints between image triplets. Continuous, recursive calibration refinement is obtained with a robust, adapted iterated extended Kalman filter. To achieve high accuracy, physically relevant geometric optimization criteria are formulated in a Gauss-Helmert type model. The self-calibration framework is tested on an active stereo system. Experiments with synthetic data as well as on natural indoor and outdoor imagery indicate that the different constraints are complementing each other and thus a method combining two of the above constraints is proposed: While reduced order bundle adjustment gives by far the most accurate results (and might suffice on its own in some environments), the epipolar constraint yields instantaneous calibration that is not affected by independently moving objects in the scene. Hence, it expedites and stabilizes the calibration process.

Laboratory and field performance of megapixel QWIP focal plane arrays

We present the results of laboratory and field testing of a very large format (1024 × 1024 pixels) focal plane array (FPA) made using quantum well infrared photodetector (QWIP) technology. The FPA was produced by QWIP Technologies, Inc. and tested at the Army Research Laboratory (ARL). Tests performed included spectral response, dark current, 3d-noise, minimum resolvable temperature (MRT) and optical crosstalk. The spectral response was found to peak at 8.55 μm. The device was found to have conversion efficiency close to 10% and the level of dark current was low enough to allow background limited infrared performance (BLIP) at 76 K. The pixel operability was in excess of 97% and there were no large cluster defects. The FPA was thinned to less than 20 μm to allow thermal cycling and sharp focus. We will show indoor and outdoor imagery acquired with the FPA. The FPA was installed in a camera system that was taken to a major field test. We will show initial results of the analysis of the image data collected at that test. Vehicles of military interest were imaged at ranges between 500 m and 5 km.

Inertial navigation sensor integrated motion analysis for autonomous vehicle navigation

Many types of existing vehicles contain an inertial navigation system (INS) that can be utilized to greatly improve the performance of motion analysis techniques and make them useful for practical military and civilian applications. This article presents the results obtained with a maximally passive system of obstacle detection for ground-based vehicles and rotorcraft. Automatic detection of these obstacles and the necessary guidance and control actions triggered by such detection will facilitate autonomous vehicle navigation. Our approach to obstacle detection employs motion analysis of imagery collected by a passive sensor during vehicle travel to generate range measurements to world points within the field of view of the sensor. The approach makes use of INS data and scene analysis results to improve interest point selection, the matching of the interest points, and the subsequent motion-based range computations, tracking, and obstacle detection. In this article, we concentrate on the results obtained using lab and outdoor imagery. The range measurements that are made by INS integrated motion analysis are compared to a limited amount of ground truth that is available. © 1992 John Wiley & Sons, Inc.

Context-based vision: recognizing objects using information from both 2D and 3D imagery

Results from an ongoing project concerned with recognizing objects in complex scene domains, especially in the domain that includes the natural outdoor world, are described. Traditional machine recognition paradigms assume either that all objects of interest are definable by a relatively small number of explicit shape models or that all objects of interest have characteristic, locally measurable features. The failure of both assumptions has a dramatic impact on the form of an acceptable architecture for an object recognition system. In this work, the use of the contextual information is a central issue, and a system is explicitly designed to identify and use context as an integral part of recognition that eliminates the traditional dependence on stored geometric models and universal image partitioning algorithms. This paradigm combines the results of many simple procedures that analyze monochrome, color, stereo, or 3D range images. Interpreting the results along with relevant contextual knowledge makes it possible to achieve a reliable recognition result, even when using imperfect visual procedures. Initial experimentation with the system on ground-level outdoor imagery has demonstrated competence beyond what is attainable with other vision systems. >

Toward the unsupervised interpretation of outdoor imagery

A new approach to the interpretation of outdoor scenes is described. It is based on a context-sensitive classifier which uses relative constraints to describe global relationships between object classes. Contextual models represent the structure of a scene's underlying feature space in terms of stable, physically based parameters. A discrete relaxation algorithm is used to find unambiguous labelings that satisfy a set of ordering relations between object classes. Unlike rule-based systems, these constraints provide a complete and consistent description of the scene. Scenes that are similar in structure are organized into contexts, each of which is represented by a consistent set of constraints. Instead of attempting to achieve a high degree of specificity and localization within limited domains, the methodology is geared toward recognizing general kinds of objects with little or no human intervention over a wider range of scenes. Several examples which demonstrate the recognition of simple objects in black-and-white and multispectral imagery acquired by aircraft, satellite, and at ground level are presented. Through a series of experiments, the ability of the system to degrade gracefully in performance when faced with new and unknown situations is demonstrated.

Display of wide dynamic range infrared images from PtSi Schottky barrier cameras

Twelve-bit digitized images taken with PtSi Schottky barrier detector arrays have been processed on Sun work stations. Two techniques for 8-bit global display are compared: the standard method of histogram equalization and a newly devised technique of histogram projection. The latter assigns equal dynamic range to each occupied level, while the former does so according to the density of the occupied levels. The projection technique generally gives distinctly superior results based on an extensive set of indoor, outdoor, day, and night imagery. For cases in which the two algorithms have complementary advantages, the techniques can be combined in effect by a weighting of their distribution functions, which often gives the desirable features of each. The new projection algorithm also can be used as a powerful and robust local contrast enhancement technique. An alternative method of contrast enhancement, a global algorithm based on modular (sawtooth) displays, affords a comparable degree of enhancement at less computational cost.