The goal of this paper is twofold: firstly, to provide a novel mathematical model that describes the kinematic chain of motion of the human fingers based on Lagrangian mechanics with four degrees of freedom and secondly, to estimate the model parameters using data from able-bodied individuals. In the literature there are a variety of mathematical models that have been developed to describe the motion of the human finger. These models offer little to no information on the underlying mechanisms or corresponding equations of motion. Furthermore, these models do not provide information as to how they scale with different anthropometries. The data used here is generated using an experimental procedure that considers the free response motion of each finger segment with data captured via a motion capture system. The angular data collected are then filtered and fitted to a linear second-order differential approximation of the equations of motion. The results of the study show that the free response motion of the segments is underdamped across flexion/extension and ad/abduction.

Current camera traps use passive infrared triggers; therefore, they only capture images when animals have a substantially different surface body temperature than the background. Endothermic animals, such as mammals and birds, provide adequate temperature contrast to trigger cameras, while ectothermic animals, such as amphibians, reptiles, and invertebrates, do not. Therefore, a camera trap that is capable of monitoring ectotherms can expand the capacity of ecological research on ectothermic animals. This study presents the design, development, and evaluation of a solar-powered and artificial-intelligence-assisted camera trap system with the ability to monitor both endothermic and ectothermic animals. The system is developed using a central processing unit, integrated graphics processing unit, camera, infrared light, flash drive, printed circuit board, solar panel, battery, microphone, GPS receiver, temperature/humidity sensor, light sensor, and other customized circuitry. It continuously monitors image frames using a motion detection algorithm and commences recording when a moving animal is detected during the day or night. Field trials demonstrate that this system successfully recorded a high number of animals. Lab testing using artificially generated motion demonstrated that the system successfully recorded within video frames at a high accuracy of 0.99, providing an optimized peak power consumption of 5.208 W. No water or dust entered the cases during field trials. A total of 27 cameras saved 85,870 video segments during field trials, of which 423 video segments successfully recorded ectothermic animals (reptiles, amphibians, and arthropods). This newly developed camera trap will benefit wildlife biologists, as it successfully monitors both endothermic and ectothermic animals.

COVID-19 has restricted outdoor exercise and hospital visits for rehabilitation therapy. Home-based training and rehabilitation coaching systems have emerged as a way to overcome these circumstances. Conventional optical motion-capture systems, such as VICON, have been used for measuring precise movement and providing posture feedback during exercise or rehabilitation; however, its application is limited to professional facilities because of its high cost and space requirement. To extend the applicability to home-based use, we designed wearable skin markers (WSMs) with body segment-specific patterns that can be detected by low-cost web cameras. WSMs are band-shaped and stretchable and thus can be worn like cloth, with minimal effort for placement. The body segment-specific patterns enable real-time data processing, which reduces the marker data post-processing time. A 6-degree-of-freedom (DOF) pose for each WSM is obtained by recognizing the segment-specific patterns; the 3D configuration of the contoured corners of the patterns found by triangulation is then utilized to construct the coordinates of each WSM. The WSM system was validated via three experiments. The robustness of marker recognition was evaluated by measuring the false-positive and false-negative rates of WSM. For accuracy validation, the angle estimation results were obtained for the mechanical joint of a 3-DOF gimbal and lower-limb joints of a walking human subject and compared to the reference systems. The gimbal experiment was included to evaluate the accuracy of our system in the condition with no skin movement artifact. The maximum standard deviation of the difference between WSM and the encoder was 0.9 °   for the gimbal experiment, and that between WSM and VICON was 5.0 ° for the human experiment. The accuracy was comparable to the reference systems, making it suitable for home environment application.

Variations in the quantity of plankton impact the entire marine ecosystem. It is of great significance to accurately assess the dynamic evolution of the plankton for monitoring the marine environment and global climate change. In this paper, a novel method is introduced for deep-sea plankton community detection in marine ecosystem using an underwater robotic platform. The videos were sampled at a distance of 1.5 m from the ocean floor, with a focal length of 1.5-2.5 m. The optical flow field is used to detect plankton community. We showed that for each of the moving plankton that do not overlap in space in two consecutive video frames, the time gradient of the spatial position of the plankton are opposite to each other in two consecutive optical flow fields. Further, the lateral and vertical gradients have the same value and orientation in two consecutive optical flow fields. Accordingly, moving plankton can be accurately detected under the complex dynamic background in the deep-sea environment. Experimental comparison with manual ground-truth fully validated the efficacy of the proposed methodology, which outperforms six state-of-the-art approaches.

A feasibility study was conducted to investigate the use of a wearable gait analysis system for classifying gait speed using a low-cost wearable camera in a semi-structured indoor setting. Data were collected from 19 participants who wore the system during indoor walk sequences at varying self-determined speeds (slow, medium, and fast). Gait parameters using this system were compared with parameters obtained from a vest comprising of a single triaxial accelerometer and from a marker-based optical motion-capture system. Computer-vision techniques and signal processing methods were used to generate frequency-domain gait parameters from each gait-recording device, and those parameters were analysed to determine the effectiveness of the different measurement systems in discriminating gait speed. Results indicate that the authors\' low-cost, portable, vision-based system can be effectively used for in-home gait analysis.

Automatic recognition of instruments in laparoscopy videos poses many challenges that need to be addressed, like identifying multiple instruments appearing in various representations and in different lighting conditions, which in turn may be occluded by other instruments, tissue, blood, or smoke. Considering these challenges, it may be beneficial for recognition approaches that instrument frames are first detected in a sequence of video frames for further investigating only these frames. This pre-recognition step is also relevant for many other classification tasks in laparoscopy videos, such as action recognition or adverse event analysis. In this work, the authors address the task of binary classification to recognise video frames as either instrument or non-instrument images. They examine convolutional neural network models to learn the representation of instrument frames in videos and take a closer look at learned activation patterns. For this task, GoogLeNet together with batch normalisation is trained and validated using a publicly available dataset for instrument count classifications. They compared transfer learning with learning from scratch and evaluate on datasets from cholecystectomy and gynaecology. The evaluation shows that fine-tuning a pre-trained model on the instrument and non-instrument images is much faster and more stable in learning than training a model from scratch.

Depth estimation plays an important role in vision-based laparoscope surgical navigation systems. Most learning-based depth estimation methods require ground truth depth or disparity images for training; however, these data are difficult to obtain in laparoscopy. The authors present an unsupervised learning depth estimation approach by fusing traditional stereo knowledge. The traditional stereo method is used to generate proxy disparity labels, in which unreliable depth measurements are removed via a confidence measure to improve stereo accuracy. The disparity images are generated by training a dual encoder-decoder convolutional neural network from rectified stereo images coupled with proxy labels generated by the traditional stereo method. A principled mask is computed to exclude the pixels, which are not seen in one of views due to parallax effects from the calculation of loss function. Moreover, the neighbourhood smoothness term is employed to constrain neighbouring pixels with similar appearances to generate a smooth depth surface. This approach can make the depth of the projected point cloud closer to the real surgical site and preserve realistic details. The authors demonstrate the performance of the method by training and evaluation with a partial nephrectomy da Vinci surgery dataset and heart phantom data from the Hamlyn Centre.

Repeat Image Feature Tracking (RIFT) is commonly used to measure glacier surface motion from pairs of images, most often utilizing normalized cross correlation (NCC). The Multiple-Image Multiple-Chip (MIMC) algorithm successfully employed redundant matching (i.e. repeating the matching process over each area using varying combinations of settings) to increase the matching success rate. Due to the large number of repeat calculations, however, the original MIMC algorithm was slow and still prone to failure in areas of high shearing flow. Here we present several major updates to the MIMC algorithm that increase both speed and matching success rate. First, we include additional redundant measurements by swapping the image order and matching direction; a process we term Quadramatching. Second, we utilize a priori ice velocity information to confine the NCC search space through a system we term dynamic linear constraint (DLC), which substantially reduces the computation time and increases the rate of successful matches. Additionally, we develop a novel post-processing algorithm, pseudosmoothing, to determine the most probable displacement. Our tests reveal the complimentary and multiplicative nature of these upgrades in their improvement in overall MIMC performance.

Cerebrovascular surgery treats vessel abnormalities in the brain and spinal cord, including arteriovenous malformations (AVMs) and aneurysms. These procedures often involve clipping the vessels feeding blood to these abnormalities, making accurate classification of blood vessel types (feeding versus draining) important during surgery. Previous work to guide the intraoperative identification of the vessels included augmented reality (AR) using pre-operative images, injected dyes, and Doppler ultrasound, but each with their drawbacks. The authors propose and demonstrate a novel technique to help differentiate vessels by enhancing short videos of a few seconds from the surgical microscope using motion magnification and spectral analysis, and constructing AR views that fuse the analysis results as intuitive colourmaps and the surgical microscopic view. They demonstrated the proposed technique retrospectively with two real cerebrovascular surgical cases: one AVM and one aneurysm. The results showed that the proposed technique can help characterise different vessel types (feeding and draining the abnormality), which agree with those identified by the operating surgeon.

OBJECTIVE: To examine the impact of 4D-PET on target volume delineation of upper-abdominal tumors, versus conventional un-gated PET.
METHODS: Four patients with upper-abdominal tumors underwent respiratory-correlated FDG PET/CT scanning (4D-PET) as part of a continuing IRB-approved research protocol. Internal target volumes of FDG-avid tumors were contoured on the 4D-PET and conventional un-gated PET by a radiation oncologist who is a specialist in gastro-intestinal tumors. To create the 4D-PET ITV, the end-inhale and end-exhale 4D-PET phases were used. The relative volumes and volumetric overlaps of the 4D and un-gated target volumes were examined. Additionally, 4D-PET was used to measure the motion of the tumors.
RESULTS: Of the four patients who were imaged, one showed minimal motion (〈 3 mm in any direction) and one showed minimal FDG avidity; these were removed from further analysis. Of the two tumors which showed significant motion and FDG uptake, 4D-PET volumes were 28% and 21% larger than un-gated PET volumes. The un-gated PET volumes were almost entirely contained within the 4D-PET volumes (95% and 93% for the two tumors). Tumors appeared to deform as well as translate with breathing, although this could be due to varying intra-gate motion rather than actual physiological deformation. The superior-inferior borders of the tumors exhibited the most motion, with displacements of 5.6 mm and 6.4 mm.
CONCLUSIONS: 4D-PET can be used to estimate the motion of FDG-avid upper-abdominal tumors. Use of 4D-PET increases the size of target volumes compared to un-gated PET in a subset of upper-abdominal cancer patients. Direct measurement of tumor motion and deformation by 4D-PET imaging could allow the use of patient-specific margins rather than population-based margins, potentially leading to increased target coverage and reduced normal tissue irradiation.