Search

Simple Summary: Animal movement trajectories are effective indicators of key information such as social behavior, food acquisition, reproduction, migration, and survival strategies in animal behavior analysis. However, manual observation is still relied upon in many analysis scenarios, which is inefficient and error-prone. This paper introduces a computer vision-based method for tracking animal trajectories, which enables monitoring and accurate acquisition of individual target animal movement trajectories over extended periods, overcoming the limitations of manual observation. The experiments demonstrate that the method is efficient and accurate in tracking animals in complex scenes, providing essential basic data for animal behavior analysis and having a wide range of potential applications. Animal tracking is crucial for understanding migration, habitat selection, and behavior patterns. However, challenges in video data acquisition and the unpredictability of animal movements have hindered progress in this field. To address these challenges, we present a novel animal tracking method based on correlation filters. Our approach integrates hand-crafted features, deep features, and temporal context information to learn a rich feature representation of the target animal, enabling effective monitoring and updating of its state. Specifically, we extract hand-crafted histogram of oriented gradient features and deep features from different layers of the animal, creating tailored fusion features that encapsulate both appearance and motion characteristics. By analyzing the response map, we select optimal fusion features based on the oscillation degree. When the target animal's state changes significantly, we adaptively update the target model using temporal context information and robust feature data from the current frame. This updated model is then used for re-tracking, leading to improved results compared to recent mainstream algorithms, as demonstrated in extensive experiments conducted on our self-constructed animal datasets. By addressing specific challenges in animal tracking, our method offers a promising approach for more effective and accurate animal behavior research. [ABSTRACT FROM AUTHOR]

Abstract Correlation filter-based trackers have made significant progress in visual object tracking for various types of unmanned aerial vehicle (UAV) applications due to their promising performance and efficiency. However, the boundary effect remains a challenging problem. Several methods enlarge search areas to handle this shortcoming but introduce more background noise, and the filter is prone to learn from distractors. To address this issue, we present spatial regularized correlation filters with response consistency and distractor repression. Specifically, a temporal constraint is introduced to reinforce the consistency across frames by minimizing the difference between consecutive correlation response maps. A dynamic spatial constraint is also integrated by exploiting the local maximum points of the correlation response produced during the detection phase to mitigate the interference from background distractions. The proposed appearance model can optimize the temporal and spatial constraints together with a spatial regularization weight simultaneously. Meanwhile, the proposed appearance model can be solved effectively based on the alternating direction method of multipliers algorithm. The spatial and temporal information concealed in the response maps is fully taken into consideration to boost overall tracking performance. Extensive experiments are conducted on a public UAV benchmark dataset with 123 challenging sequences. The experimental results and analysis demonstrate that the proposed method outperforms 12 state-of-the-art trackers in terms of both accuracy and robustness while efficiently operating in real time.

Correlation filter-based trackers have made significant progress in visual object tracking for various types of unmanned aerial vehicle (UAV) applications due to their promising performance and efficiency. However, the boundary effect remains a challenging problem. Several methods enlarge search areas to handle this shortcoming but introduce more background noise, and the filter is prone to learn from distractors. To address this issue, we present spatial regularized correlation filters with response consistency and distractor repression. Specifically, a temporal constraint is introduced to reinforce the consistency across frames by minimizing the difference between consecutive correlation response maps. A dynamic spatial constraint is also integrated by exploiting the local maximum points of the correlation response produced during the detection phase to mitigate the interference from background distractions. The proposed appearance model can optimize the temporal and spatial constraints together with a spatial regularization weight simultaneously. Meanwhile, the proposed appearance model can be solved effectively based on the alternating direction method of multipliers algorithm. The spatial and temporal information concealed in the response maps is fully taken into consideration to boost overall tracking performance. Extensive experiments are conducted on a public UAV benchmark dataset with 123 challenging sequences. The experimental results and analysis demonstrate that the proposed method outperforms 12 state-of-the-art trackers in terms of both accuracy and robustness while efficiently operating in real time. [ABSTRACT FROM AUTHOR]

The underground mine environment is dangerous and harsh, tracking and detecting humans based on computer vision is of great significance for mine safety monitoring, which will also greatly facilitate identification of humans using the symmetrical image features of human organs. However, existing methods have difficulty solving the problems of accurate identification of humans and background, unstable human appearance characteristics, and humans occluded or lost. For these reasons, an improved aberrance repressed correlation filter (IARCF) tracker for human tracking in underground mines based on infrared videos is proposed. Firstly, the preprocess operations of edge sharpening, contrast adjustment, and denoising are used to enhance the image features of original videos. Secondly, the response map characteristics of peak shape and peak to side lobe ratio (PSLR) are analyzed to identify abnormal human locations in each frame, and the method of calculating the image similarity by generating virtual tracking boxes is used to accurately relocate the human. Finally, using the value of PSLR and the highest peak point of the response map, the appearance model is adaptively updated to further improve the robustness of the tracker. Experimental results show that the average precision and success rate of the IARCF tracker in the five underground scenarios reach 0.8985 and 0.7183, respectively, and the improvement of human tracking in difficult scenes is excellent. The IARCF tracker can effectively track underground human targets, especially occluded humans in complex scenes. [ABSTRACT FROM AUTHOR]

Background: The Integral Quality Monitor (IQM®) is an independent online dosimetry device attached to the treatment machine to monitor the accuracy of radiation delivery. Objective: This study investigates the influence of beam segment size and displacement as projected onto the IQM chamber on the signals and determine how individual signals can be added to get a combined segment signal made up of smaller segments.Material and Methods: This is an experimental original research type of study. IQM response maps were generated by irradiating the IQM sensitive area with small elementary segments and measuring their corresponding signals per monitor unit (MU). The output signal/MU was measured for regular and irregular fields and compared with the predicted signal/MU obtained from decomposing the open segment into a set of smaller regular segments and summing their signals from their respective response maps. The dependence of signals on segment size, shape, location and combination was investigated. Results: Predicted signals were calculated within 95-98 % accuracy for regular fields and 90-98% for irregular fields. More uniform fluence contain distribution for larger segments was observed. Response maps were consistent with the geometrical symmetry in the chamber’s wedge shape and the symmetry in the linac fluence. Conclusion: The field decomposition method allows the pre-calculation of known segment output signals per MU within 2% error, although the accuracy drops significantly for smaller, irregular fields. A method of correcting predicted signals in smaller segments needs to be laid down to get a better match with measured signals.

Nowadays, visual object tracking becomes a hotspot and difficulty to achieve a real-time and accurate target tracking, but the Siamese network has solved these difficulties because of its good tracking effect and real-time performance. The location of the target in the previous frame is the template, and the similarity matching is carried out in the search area of the current frame. However, it uses Alexnet network with simple structure and fewer layers to extract features, and just uses a score map to predict the final position of the object. Aiming at these problems, in this paper, we propose the Siamese network of fused response map that use the Alexnet network with fine tuning to extract target features, and weight fusion of score maps to estimate the final position of object. Sufficient experiments on the VOT2015 and OTB100 benchmarks validate that our tracker can improve tracking performance, and perform at 60FPS.

Background: The Integral Quality Monitor (IQM®) is an independent online dosimetry device attached to the treatment machine to monitor the accuracy of radiation delivery. Objective: This study investigates the influence of beam segment size and displacement as projected onto the IQM chamber on the signals and determine how individual signals can be added to get a combined segment signal made up of smaller segments. Material and Methods: This is an experimental original research type of study. IQM response maps were generated by irradiating the IQM sensitive area with small elementary segments and measuring their corresponding signals per monitor unit (MU). The output signal/MU was measured for regular and irregular fields and compared with the predicted signal/MU obtained from decomposing the open segment into a set of smaller regular segments and summing their signals from their respective response maps. The dependence of signals on segment size, shape, location and combination was investigated. Results: Predicted signals were calculated within 95-98 % accuracy for regular fields and 90-98% for irregular fields. More uniform fluence contain distribution for larger segments was observed. Response maps were consistent with the geometrical symmetry in the chamber's wedge shape and the symmetry in the linac fluence. Conclusion: The field decomposition method allows the pre-calculation of known segment output signals per MU within 2% error, although the accuracy drops significantly for smaller, irregular fields. A method of correcting predicted signals in smaller segments needs to be laid down to get a better match with measured signals. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this work is the three‐dimensional characterization of the active volumes of commercial solid‐state dosimetry detectors. Detailed knowledge of the dimensions of the detector's active volume as well as the detector housing is of particular interest for small‐field photon dosimetry. As shown in previous publications from different groups, the design of the detector housing influences the detector signal for small photon fields. Therefore, detailed knowledge of the active volume dimension and the surrounding materials form the basis for accurate Monte Carlo simulations of the detector. Methods: A 10 MeV proton beam focused by the microbeam system of the Physikalisch‐Technische Bundesanstalt was used to measure two‐dimensional response maps of a synthetic diamond detector (microDiamond, type 60019, PTW Freiburg) and two silicon detectors (microSilicon, type 60023, PTW Freiburg and Diode E, type 60017, PTW Freiburg). In addition, the thickness of the active volume of the new microSilicon was measured using the method developed in a previous study. Results: The analysis of the response maps leads to active area of 1.18 mm2 for the Diode E, 1.75 mm2 for the microSilicon, and 3.91 mm2 for the microDiamond detector. The thickness of the active volume of the microSilicon detector was determined to be (17.8 ± 2) µm. Conclusions: This study provides detailed geometrical data of the dosimetric active volume of three different solid‐state detector types. [ABSTRACT FROM AUTHOR]

Purpose: Dosimetry of ionizing radiation in the presence of strong magnetic fields is gaining increased relevance in light of advances for MRI‐guided radiation therapy. While the impact of strong magnetic fields on the overall response of ionization chambers has been simulated and measured before, this work investigates the local impact of the magnetic field on dose response in an ion chamber. High‐resolution 1D and 2D response maps have been created for two small clinical thimble ionization chambers, the PinPoint chambers 31006 and 31014 (Physikalisch Technische Werkstaetten Freiburg, Germany). Methods: Working on the Imaging and Medical Beam Line of the Australian Synchrotron an intense kilovoltage radiation beam with very low divergence, collimated to 0.1 mm was used to scan the chambers by moving them on a 2D motion platform. Measured current and beam position were correlated to create the response maps. Small neodymium magnets were used to create a field of about 0.25 T. Chamber axis, magnetic field, and beam direction were perpendicular to each other. Measurements were performed with both orientations of the magnetic field as well as without it. Chamber biases of 5 and 250 V in both polarities were used. Results: The local distribution of the response of small thimble‐type ionization chambers was found to be impacted by a magnetic field. Depending on the orientation of the magnetic field, the chamber response near the stem was either enhanced or reduced with the response near the tip behaving the opposite way. Local changes were in the order of up to 40% compared to measurements without the magnetic field present. Bending of the central electrode was observed for the chamber with the steel electrode. The size of the volume of reduced collection near the guard electrode was impacted by the magnetic field. As the here investigated beam and field parameters differ from those of clinical systems, quantitatively different results would be expected for the latter. However, the gyroradii encountered here were similar to those of a 6–7 MV MRI linac with a 1.5 T magnet. Conclusions: Magnetic fields impact the performance of ionization chambers also on a local level. For practical measurements this might mean a change in the effective point of measurement, in addition to any global corrections. Further knowledge about the local response will help in selecting or constructing optimized chambers for use in magnetic fields. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The problem of realisation of a monotone response map as a monotone initialised system on a finite dimensional Euclidean state space is investigated. The dynamical part of the system is described by a delta differential equation on an arbitrary time scale. This incorporates continuous- and discrete-time systems. The main result states necessary and sufficient conditions for existence of a monotone realisation of a particular class. The criterion is expressed in the language of skew differential global universes. [ABSTRACT FROM AUTHOR]

Auditory signals that contain coherent level fluctuations of a masker in different frequency regions enhance the detectability of an embedded sinusoidal target signal, an effect commonly known as comodulation masking release (CMR). Neural correlates have been proposed at different stages of the auditory system. While later stages seem to suppress the response to the masker, earlier stages are more likely to enhance their response to the signal when the masker is comodulated. Using a flanking band masking paradigm, the present study investigates how CMR is represented at the level of the inferior colliculus of the Mongolian gerbil. The responses to a target signal at various sound pressure levels in three different masking conditions were compared. In one condition the masker was a 10-Hz amplitude modulated sinusoid centered at the signal frequency while in the other two conditions six off-frequency carriers (flanking bands) were added. For 64 of a total of 94 units, the addition of comodulated flanking bands to the on-frequency masker did not change the response to the target signal. The remaining 30 units showed a change that enhanced target detectability if coherent flanking bands were added, indicative of CMR. The current data demonstrate that the response characteristics of these neurons represent an intermediate stage between the representation in the cochlear nucleus and the auditory cortex by increasing the response during the signal intervals and decreasing the response for the following masker portions. [ABSTRACT FROM AUTHOR]

The localization of object parts in the component-based object detection is among the main tasks to solve. This paper presents several improvements of the proposed local image descriptor based on Gabor wavelets. Including these descriptors in the desired application is an ambitious challenge if we take into account the high number of parameters. Determining of parameters can be very hard because of their infinite definition range. Defining the filters is done in two stages: a theoretical consideration narrows the domain and the cardinality of parameters; this is followed by adequate experiments to select the most characteristic descriptor for a target image patch. The descriptor is created from a given number of 2D Gabor filters chosen by the GentleBoost learning algorithm. Comparing the proposed descriptor to those found in the state of the art, we can conclude that the selected filters are adaptable to any target object. In contrast to this, the majority of filter-based descriptors have fixed values for the parameters that do not allow to be ductile to the given object. Parameters fine-tuning allows the descriptor to be general, and discriminative at the same time. The effect of the following experiments has been analyzed during the investigation: elimination of redundancy between the weak classifiers, using the LoG interest points in the detection process. Finally, we propose an acceleration algorithm in order to deter- mine the response map faster. By means of the descriptor, the response map is created, which accurately localizes the target object part and can easily be integrated in almost all detection systems. [ABSTRACT FROM AUTHOR]

Acoustic trauma damages the cochlea but secondarily modifies circuits of the central auditory system. Changes include decreases in inhibitory neurotransmitter systems, degeneration and rewiring of synaptic circuits, and changes in neural activity. Little is known about the consequences of these changes for the representation of complex sounds. Here, we show data from the dorsal cochlear nucleus (DCN) of rats with a moderate high-frequency hearing loss following acoustic trauma. Single-neuron recording was used to estimate the organization of neurons' receptive fields, the balance of inhibition and excitation, and the representation of the spectra of complex broadband stimuli. The complex stimuli had random spectral shapes (RSSs), and the responses were fit with a model that allows the quality of the representation and its degree of linearity to be estimated. Tone response maps of DCN neurons in rat are like those in other species investigated previously, suggesting the same general organization of this nucleus. Following acoustic trauma, abnormal response types appeared. These can be interpreted as reflecting degraded tuning in auditory nerve fibers plus loss of inhibitory inputs in DCN. Abnormal types are somewhat more prevalent at later times (103-376 days) following the exposure, but not significantly so. Inhibition became weaker in post-trauma neurons that retained inhibitory responses but also disappeared in many neurons. The quality of the representation of spectral shape, measured by sensitivity to the spectral shapes of RSS stimuli, was decreased following trauma; in fact, neurons with abnormal response types responded mainly to overall stimulus level, and not spectral shape. [ABSTRACT FROM AUTHOR]

The problem of realization of a positive response map as a positive initialized system on a finite dimensional Euclidean state space is investigated. The dynamical part of the system is described by a delta differential equation on an arbitrary time scale. This incorporates continuous- and discrete-time systems. The main result states necessary and sufficient conditions for existence of positive realization of a particular class. The criterion is expressed in the language of skew differential global universes. [ABSTRACT FROM AUTHOR]

Most existing trackers based on correlation filtering try to introduce different regularization items to improve the learning process of the tracking object. However, the parameters of the corresponding regularization items need to be adjusted dynamically to meet the corresponding tracking process. The regularization parameters are often fixed, so they cannot be updated for more accurate tracking. We propose a method to adaptively adjust the spatiotemporal regularization parameters during the tracking process. We make use of the important correlation between the response map and tracking quality in the tracking process of correlation filtering and introduce the confidence description index of the response map to optimize the spatiotemporal regularization parameters, so the training of correlation filtering can focus on the part with high confidence. In this way, the overfitting situation in training is reduced, and the accuracy and robustness of the tracker are enhanced. In performance evaluation experiments on the OTB2015 and DTB70 datasets, our algorithm outperforms the other comparative algorithms in terms of tracking success rate and distance accuracy, especially in complex scenarios, such as illumination variation, background clutter, out-of-view, and low resolution. [ABSTRACT FROM AUTHOR]

Abstract: The auditory responses of neurons in the dorsal cochlear nucleus (DCN) are known to be sensitive to anesthesia, and consequently many studies have used an unanesthetized, decerebrate preparation. Decerebration, however, severs multiple descending pathways to the DCN and is traumatic to the brain, and so sensory responses may be influenced. It was possible, by combining sterile surgery, animal conditioning, and mild restraint to allow recordings in awake gerbils (Merionus unguiculatus). Response maps (RMs), post-stimulus time histograms (PSTHs), and responses to notch noise stimuli were recorded in awake gerbils. Some units’ responses were compared to those from previous experiments in anesthetized and decerebrate gerbil preparations. All RM types observed in decerebrate gerbils were also observed in the awake gerbil, with the notable exception of type IV units. Type III units were still the most commonly recorded units. No significant changes were observed in either RM shape or notch noise responses. Although most awake DCN units had spontaneous activity (typically <20spikes/s), these rates were lower than those in decerebrate gerbils. Type III units’ spontaneous activity rates were significantly different from those in the decerebrate prep (P <0.05). DCN neurons may be more inhibited in awake gerbils. Although type III units were most sensitive to spectral notches, different unit types seem to respond slightly differently to notch noise. This study indicates that responses of DCN units in awake and decerebrate gerbils are different, though the shapes of RMs are the same. [Copyright &y& Elsevier]

The detection of a signal in noise is enhanced when the masking noise is coherently modulated over a wide range of frequencies. This phenomenon, known as comodulation masking release (CMR), has been attributed to across-channel processing; however, the relative contribution of different stages in the auditory system to such across-channel processing is unknown. It has been hypothesized that wideband or lateral inhibition may underlie a physiological correlate of CMR. To further test this hypothesis, we have measured the responses of single units from the dorsal cochlear nucleus in which wideband inhibition is particularly pronounced. Using a sinusoidally amplitude-modulated tone at the best frequency of each unit as a masker, a pure-tone signal was added in the dips of the masker modulation. Flanking bands (FBs, also amplitude-modulated pure tones) were positioned to fall within the inhibitory sidebands of the receptive field of the unit. The FBs were either in phase (comodulated) or out of phase (codeviant) with the on-frequency masker. For the majority of units, the addition of the comodulated FBs produced a strong reduction in the response to the masker modulation, making the signal more salient in the poststimulus time histograms. The change in spike rate in response to the signal between the masker and signal-plus-masker conditions was greatest for the comodulated condition for 29 of 45 units. These results are consistent with the hypothesis that wideband inhibition may play a role in across-channel processing at an early stage in the auditory pathway. [ABSTRACT FROM AUTHOR]