The Perspective-n-Point (PnP) problem has been widely studied in both computer vision and photogrammetry societies. With the development of feature extraction techniques, a large number of feature points might be avai...
The Perspective-n-Point (PnP) problem has been widely studied in both computer vision and photogrammetry societies. With the development of feature extraction techniques, a large number of feature points might be available in a single shot. It is promising to devise a consistent estimator, i.e., the estimate can converge to the true camera pose as the number of points increases. To this end, we propose a consistent PnP solver, named CPnP, with bias elimination. Specifically, linear equations are constructed from the original projection model via measurement model modification and variable elimination, based on which a closed-form least-squares solution is obtained. We then analyze and subtract the asymptotic bias of this solution, resulting in a consistent estimate. Additionally, Gauss-Newton (GN) iterations are executed to refine the consistent solution. Our proposed estimator is efficient in terms of computations—it has $O(n)$ time complexity. Simulations and real dataset tests show that our proposed estimator is superior to some well-known ones for images with dense visual features, in terms of estimation precision and computing time.
Surgical instrument segmentation is crucial in surgical scene understanding, thereby facilitating surgical safety. Existing algorithms directly detected all instruments of predefined categories in the input image, lac...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
Surgical instrument segmentation is crucial in surgical scene understanding, thereby facilitating surgical safety. Existing algorithms directly detected all instruments of predefined categories in the input image, lacking the capability to segment specific instruments according to the surgeon’s intention. During different stages of surgery, surgeons exhibit varying preferences and focus toward different surgical instruments. Therefore, an instrument segmentation algorithm that adheres to the surgeon’s intention can minimize distractions from irrelevant instruments and assist surgeons to a great extent. The recent Segment Anything Model (SAM) reveals the capability to segment objects following prompts, but the manual annotations for prompts are impractical during the surgery. To address these limitations in operating rooms, we propose an audio-driven surgical instrument segmentation framework, named ASI-Seg, to accurately segment the required surgical instruments by parsing the audio commands of surgeons. Specifically, we propose an intention-oriented multimodal fusion to interpret the segmentation intention from audio commands and retrieve relevant instrument details to facilitate segmentation. Moreover, to guide our ASI-Seg segment of the required surgical instruments, we devise a contrastive learning prompt encoder to effectively distinguish the required instruments from the irrelevant ones. Therefore, our ASI-Seg promotes the workflow in the operating rooms, thereby providing targeted support and reducing the cognitive load on surgeons. Extensive experiments are performed to validate the ASI-Seg framework, which reveals remarkable advantages over classical state-of-the-art and medical SAMs in both semantic segmentation and intention-oriented segmentation. The source code is available at https://***/Zonmgin-Zhang/ASI-Seg.
Distributed tactile sensing for multi-force detection is crucial for various aerial robot interaction tasks. However, current contact sensing solutions on drones only exploit single end-effector sensors and cannot pro...
详细信息
Different from traditional vehicles, the routing problem of electric vehicles (EVs) is closely coupled with their charging. Hence, operating EV requires a joint optimization of both routing and charging. Moreover, the...
详细信息
Different from traditional vehicles, the routing problem of electric vehicles (EVs) is closely coupled with their charging. Hence, operating EV requires a joint optimization of both routing and charging. Moreover, the travel time and energy consumption uncertainties also bring challenges to the EV operation in practice. In this paper, we study the routing and charging problem of EVs under the chance constrained optimization framework, where uncertainties are tackled with probabilistic constraints. An iterative algorithm is proposed, which transforms the original challenging mixed-integer nonlinear program into the iteration of two linear programs. The finite convergence of this algorithm is also proved. Numerical results show that our proposed algorithm can achieve near-optimal solutions in rather short computation times.
Forests cover nearly one-third of the Earth’s land and are some of our most biodiverse ecosystems. Due to climate change, these essential habitats are endangered by increasing wildfires. Wildfires are not just a risk...
Forests cover nearly one-third of the Earth’s land and are some of our most biodiverse ecosystems. Due to climate change, these essential habitats are endangered by increasing wildfires. Wildfires are not just a risk to the environment, but they also pose public health risks. Given these issues, there is an indispensable need for efficient and early detection methods. Conventional detection approaches fall short due to spatial limitations and manual feature engineering, which calls for the exploration and development of data-driven deep learning solutions. This paper, in this regard, proposes 'FireXnet', a tailored deep learning model designed for improved efficiency and accuracy in wildfire detection. FireXnet is tailored to have a lightweight architecture that exhibits high accuracy with significantly less training and testing time. It contains considerably reduced trainable and non-trainable parameters, which makes it suitable for resource-constrained devices. To make the FireXnet model visually explainable and trustable, a powerful explainable artificial intelligence (AI) tool, SHAP (SHapley Additive exPlanations) has been incorporated. It interprets FireXnet’s decisions by computing the contribution of each feature to the prediction. Furthermore, the performance of FireXnet is compared against five pre-trained models — VGG16, InceptionResNetV2, InceptionV3, DenseNet201, and MobileNetV2 — to benchmark its efficiency. For a fair comparison, transfer learning and fine-tuning have been applied to the aforementioned models to retrain the models on our dataset. The test accuracy of the proposed FireXnet model is 98.42%, which is greater than all other models used for comparison. Furthermore, results of reliability parameters confirm the model’s reliability, i.e., a confidence interval of [0.97, 1.00] validates the certainty of the proposed model’s estimates and a Cohen’s kappa coefficient of 0.98 proves that decisions of FireXnet are in considerable accordance with t
The immense value of IoT data in real-time applications has led to the rise of fresh IoT data trading. Existing research often neglects strategic users who optimally time their data purchases, significantly affecting ...
详细信息
UAVs have great potential when applied to persistent monitoring, but there are still problems such as difficulty in ensuring the monitoring frequency and easy leakage of monitoring path information. Therefore, it is n...
详细信息
ISBN:
(纸本)9781665478977
UAVs have great potential when applied to persistent monitoring, but there are still problems such as difficulty in ensuring the monitoring frequency and easy leakage of monitoring path information. Therefore, it is necessary to increase the UAV monitoring frequency of targets and the randomness of monitoring paths as much as possible on the premise of covering all monitoring tasks. In response to the above problems, this paper studies the UAV path planning problem of simultaneous optimization of monitoring frequency and path security. Through the evaluation of monitoring frequency and path security based on monitoring overdue time and path entropy, a mathematical model for UAV path planning is established. An improved ant colony algorithm based on the monitoring overdue time (Overdue-aware Ant Colony Optimization, OACO) is designed, and finally the UAV flight trajectory with high monitoring frequency and the high monitoring path security is obtained. The simulation results show that the method proposed in this paper can effectively improve the monitoring frequency of each monitoring node to be accessed, improve the security of the UAV monitoring path, which is of great significance for enhancing monitoring security and preventing intrusion.
As CMOS processes continue to shrink, nano-scale CMOS latches have become increasingly sensitive to multiple-node upset (MNU) errors caused by radiation. To tolerate MNU, a novel quadruple-node-upset (QNU) self-recove...
As CMOS processes continue to shrink, nano-scale CMOS latches have become increasingly sensitive to multiple-node upset (MNU) errors caused by radiation. To tolerate MNU, a novel quadruple-node-upset (QNU) self-recoverable latch is proposed in this paper. The proposed latch is mainly constructed from six blocks of three-level C-elements (TLCEs) and six inverters. With the mutual feedback of the various TLCEs, the proposed latch can recover from any QNU. Furthermore, due to the clock gating methodology and a high-speed transmission path, the proposed latch has lower overhead in terms of power dissipation and transmission delay. Simulation results show that the proposed latch achieves high reliability with moderate overhead compared to typical existing latches.
Integrating a prosthetic hand to amputees with seamless neural compatibility presents a grand challenge to neuroscientists and neural engineers for more than half *** anatomical structure or appearance of human hand d...
详细信息
Integrating a prosthetic hand to amputees with seamless neural compatibility presents a grand challenge to neuroscientists and neural engineers for more than half *** anatomical structure or appearance of human hand does not lead to improved neural connectivity to the sensorimotor system of *** functions of modern prosthetic hands do not match the dexterity of human hand due primarily to lack of sensory awareness and compliant ***,progress in restoring sensory feedback has marked a significant step forward in improving neural continuity of sensory information from prosthetic hands to ***,little effort has been made to replicate the compliant property of biological muscle when actuating prosthetic ***,a full-fledged biorealistic approach to designing prosthetic hands has not been contemplated in neuroprosthetic *** this perspective article,we advance a novel view that a prosthetic hand can be integrated harmoniously with amputees only if neural compatibility to the sensorimotor system is *** ongoing research supports that the next-generation prosthetic hand must incorporate biologically realistic actuation,sensing,and reflex functions in order to fully attain neural compatibility.
Many applications have an inherent tolerance for insignificant inaccuracies. Full adders are key arithmetic functions for many error-tolerant applications. Approximate full adders are considered an efficient technique...
Many applications have an inherent tolerance for insignificant inaccuracies. Full adders are key arithmetic functions for many error-tolerant applications. Approximate full adders are considered an efficient technique to trade off energy relative to performance and accuracy. In this paper, we propose four approximate full adders with low overhead. The proposed and the existing approximate full adders are classified into two groups according to their error distances. Simulation results show that, compared with the existing approximate full adders, in the first group, the proposed ones can reduce power-area-delay product (PADP) by 61.83%, power by 54.15%, area by 44.67%, and delay by 22.78 % on average; in the second group, the proposed ones can reduce PADP by 97.01%, power by 93.43%, area by 24.98%, and delay by 36.14% on average.
暂无评论