Short-term movement and retreat sites of Leptodactylus labyrinthicus (Anura : Leptodactylidae) during the breeding season: A spool-and-line tracking study

Capture/recapture studies significantly increase our knowledge of the natural history of anuran amphibians. Many different methods have been employed in these studies, but a number of new techniques still require experimental validation. During two reproductive seasons in a Cerrado remnant in southeastern Brazil, we investigated the movement patterns and habitat use of the pepper frog, Leptodactylus labyrinthicus, using a spool-and-line device. This low-cost device did not appear to interfere with the activities of the frogs and allowed for constant monitoring, showing precise routes of movement and great predictability of relocations. Both sexes were active at night. During the day, males and females made use of retreat sites under vegetation or in burrows constructed by small- and medium-sized mammals. Males and females did not use standardized routes; there were no significant differences between their movements, and movements were not correlated with body size or environmental conditions. Individuals are able to move further than 100 m per day, a characteristic that may enable this species to colonize or recolonize open areas.

Fast, Reliable Head Tracking under Varying Illumination

An improved technique for 3D head tracking under varying illumination conditions is proposed. The head is modeled as a texture mapped cylinder. Tracking is formulated as an image registration problem in the cylinder's texture map image. To solve the registration problem in the presence of lighting variation and head motion, the residual error of registration is modeled as a linear combination of texture warping templates and orthogonal illumination templates. Fast and stable on-line tracking is then achieved via regularized, weighted least squares minimization of the registration error. The regularization term tends to limit potential ambiguities that arise in the warping and illumination templates. It enables stable tracking over extended sequences. Tracking does not require a precise initial fit of the model; the system is initialized automatically using a simple 2-D face detector. The only assumption is that the target is facing the camera in the first frame of the sequence. The warping templates are computed at the first frame of the sequence. Illumination templates are precomputed off-line over a training set of face images collected under varying lighting conditions. Experiments in tracking are reported.

Fast, Reliable Head Tracking under Varying Illumination: An Approach Based on Registration of Texture-Mapped 3D Model

An improved technique for 3D head tracking under varying illumination conditions is proposed. The head is modeled as a texture mapped cylinder. Tracking is formulated as an image registration problem in the cylinder's texture map image. The resulting dynamic texture map provides a stabilized view of the face that can be used as input to many existing 2D techniques for face recognition, facial expressions analysis, lip reading, and eye tracking. To solve the registration problem in the presence of lighting variation and head motion, the residual error of registration is modeled as a linear combination of texture warping templates and orthogonal illumination templates. Fast and stable on-line tracking is achieved via regularized, weighted least squares minimization of the registration error. The regularization term tends to limit potential ambiguities that arise in the warping and illumination templates. It enables stable tracking over extended sequences. Tracking does not require a precise initial fit of the model; the system is initialized automatically using a simple 2D face detector. The only assumption is that the target is facing the camera in the first frame of the sequence. The formulation is tailored to take advantage of texture mapping hardware available in many workstations, PC's, and game consoles. The non-optimized implementation runs at about 15 frames per second on a SGI O2 graphic workstation. Extensive experiments evaluating the effectiveness of the formulation are reported. The sensitivity of the technique to illumination, regularization parameters, errors in the initial positioning and internal camera parameters are analyzed. Examples and applications of tracking are reported.

Tracking of industrial objects by using CAD models

In this paper we present a model-based approach for real-time camera pose estimation in industrial scenarios. The line model which is used for tracking is generated by rendering a polygonal model and extracting contours out of the rendered scene. By un-projecting a point on the contour with the depth value stored in the z-buffer, the 3D coordinates of the contour can be calculated. For establishing 2D/3D correspondences the 3D control points on the contour are projected into the image and a perpendicular search for gradient maxima for every point on the contour is performed. Multiple hypotheses of 2D image points corresponding to a 3D control point make the pose estimation robust against ambiguous edges in the image.

Compensation of unmodeled aircraft dynamics in airborne inspection of linear infrastructure assets

Fixed-wing aircraft equipped with downward pointing cameras and/or LiDAR can be used for inspecting approximately piecewise linear assets such as oil-gas pipelines, roads and power-lines. Automatic control of such aircraft is important from a productivity and safety point of view (long periods of precision manual flight at low-altitude is not considered reasonable from a safety perspective). This paper investigates the effect of any unwanted coupling between guidance and autopilot loops (typically caused by unmodeled delays in the aircraft’s response), and the specific impact of any unwanted dynamics on the performance of aircraft undertaking inspection of piecewise linear corridor assets (such as powerlines). Simulation studies and experimental flight tests are used to demonstrate the benefits of a simple compensator in mitigating the unwanted lateral oscillatory behaviour (or coupling) that is caused by unmodeled time constants in the aircraft dynamics.

The rodent species of the Ifugao Rice Terraces, Philippines - Target or non-target species for management?

We investigated the species diversity and habitat use of rodents in the Ifugao Rice Terraces (IRT), Luzon, Philippines, as a first step in their assessment either as pest species of rice or as potential non-target species of rodent control practice. Trapping was carried out in caneland and forest habitats adjacent to rice cropland using trap lines of 10 - 15 cage-traps. Four trapping rounds, each consisting of 5 nights trapping, were replicated at two sites during the months of May and June. A diverse rodent fauna was recorded, including the non-native pest species, Rattus tanezumi, and the native species, Rattus everetti and Chrotomys mindorensis. Results from trapping and spool-and-line tracking suggested that these native species do not contribute to rice damage and that several may actually be beneficial in the ricefield ecosystem as vermivores that feed on invertebrate pests. Control should therefore be directed at the pest species, R. tanezumi, minimising non-target effects on the non-pest rodent species.

Short-term movements of the South American rattlesnake (Crotalus durissus) in southeastern Brazil

Ecological studies of movements in animals require extensive knowledge of direction, distance and frequency of movements. The purpose of this study was to describe the daily and seasonal movements in a population of the South American rattlesnake, Crotalus durissus. The study population inhabits a cerrado area in southeastern Brazil. Snakes were tracked with externally attached radio-transmitters and thread bobbins. Larger animals tended to make more extensive daily movements, moving further from the initial site of capture. There were no differences in average daily movements between sexes. Site fidelity was higher in the dry season for both sexes. Both sexes moved distances twice as long as those calculated by drawing a straight line between consecutive points. The movement pattern of C. durissus seemed to be similar to that observed in other tropical pit vipers, such as species of the genus Bothrops.

Are tortoises important seed dispersers in Amazonian forests?

According to most studies on seed dispersal in tropical forests, mammals and birds are considered the main dispersal agents and the role played by other animal groups remains poorly explored. We investigate qualitative and quantitative components of the role played by the tortoise Chelonoidis denticulata in seed dispersal in southeastern Amazon, and the influence of seasonal variation in tortoise movement patterns on resulting seed shadows. Seed shadows produced by this tortoise were estimated by combining information on seed passage times through their digestive tract, which varied from 3 to 17 days, with a robust dataset on movements obtained from 18 adult C. denticulata monitored with radio transmitters and spoon-and-line tracking devices. A total of 4,206 seeds were found in 94 collected feces, belonging to 50 seed morphotypes of, at least, 25 plant genera. Very low rates of damage to the external structure of the ingested seeds were observed. Additionally, results of germination trials suggested that passage of seeds through C. denticulata`s digestive tract does not seem to negatively affect seed germination. The estimated seed shadows are likely to contribute significantly to the dispersal of seeds away from parent plants. During the dry season seeds were dispersed, on average, 174.1 m away from the location of fruit ingestion; during the rainy season, this mean dispersal distance increased to 276.7 m. Our results suggest that C. denticulata plays an important role in seed dispersal in Amazonian forests and highlight the influence of seasonal changes in movements on the resulting seed shadows.

Bait avoidance and habitat use by the roof rat, Rattus rattus, in a piggery

The acceptance of four anticoagulant rodenticide baits was evaluated in a piggery. The bait bases were cracked wheat, wax block, pig feed, and Racumin Paste(R). Mean daily consumption of each bait was poor (< 5 g). Mean activity index measured with tracking plates did not change significantly throughout pre-baiting (3 days), baiting (37) or post-baiting (7), indicating that the baits had no impact on the population. The same baiting regime applied simultaneously in nearby stables with lower feed availability induced a significantly higher mean consumption of the cracked wheat based bait, and the activity index declined to zero at day 23, indicating that the rats were eradicated. The failure of the baits to control rats in the piggery was possibly due to the poor bait acceptance caused by the abundant feed supply. Results of live-trapping and radio- and spool-and-line tracking indicated that the population was confined within the piggery; lower windowsills were the most used above-ground structure for movements; and minimum home range span was 17 m. We suggest that rodent control should be implemented within the confines of the piggery to reduce the risk to non-target animals, and that mortality agents should be placed less than or equal to 17 in apart arboreally for the roof rat. (C) 2004 Elsevier Ltd. All rights reserved.

Visual guidance for fixed-wing unmanned aerial vehicles using feature tracking : application to power line inspection

This thesis presents novel vision based control solutions that enable fixed-wing Unmanned Aerial Vehicles to perform tasks of inspection over infrastructure including power lines, pipe lines and roads. This is achieved through the development of techniques that combine visual servoing with alternate manoeuvres that assist the UAV in both following and observing the feature from a downward facing camera. Control designs are developed through techniques of Image Based Visual Servoing to utilise sideslip through Skid-to-Turn and Forward-Slip manoeuvres. This allows the UAV to simultaneously track and collect data over the length of infrastructure, including straight segments and the transition where these meet.

Classification-based probabilistic modeling of texture transition for fast line search tracking and delineation

We introduce a classification-based approach to finding occluding texture boundaries. The classifier is composed of a set of weak learners, which operate on image intensity discriminative features that are defined on small patches and are fast to compute. A database that is designed to simulate digitized occluding contours of textured objects in natural images is used to train the weak learners. The trained classifier score is then used to obtain a probabilistic model for the presence of texture transitions, which can readily be used for line search texture boundary detection in the direction normal to an initial boundary estimate. This method is fast and therefore suitable for real-time and interactive applications. It works as a robust estimator, which requires a ribbon-like search region and can handle complex texture structures without requiring a large number of observations. We demonstrate results both in the context of interactive 2D delineation and of fast 3D tracking and compare its performance with other existing methods for line search boundary detection.

On-line adaptive visual tracking

Visual tracking is the problem of estimating some variables related to a target given a video sequence depicting the target. Visual tracking is key to the automation of many tasks, such as visual surveillance, robot or vehicle autonomous navigation, automatic video indexing in multimedia databases. Despite many years of research, long term tracking in real world scenarios for generic targets is still unaccomplished. The main contribution of this thesis is the definition of effective algorithms that can foster a general solution to visual tracking by letting the tracker adapt to mutating working conditions. In particular, we propose to adapt two crucial components of visual trackers: the transition model and the appearance model. The less general but widespread case of tracking from a static camera is also considered and a novel change detection algorithm robust to sudden illumination changes is proposed. Based on this, a principled adaptive framework to model the interaction between Bayesian change detection and recursive Bayesian trackers is introduced. Finally, the problem of automatic tracker initialization is considered. In particular, a novel solution for categorization of 3D data is presented. The novel category recognition algorithm is based on a novel 3D descriptors that is shown to achieve state of the art performances in several applications of surface matching.