In this article, we aim to enhance the accuracy and usefulness of vision-based road segmentation for autonomous vehicles across various scenarios by actively controlling the gaze of the camera. The camera is mounted o...
详细信息
In this article, we aim to enhance the accuracy and usefulness of vision-based road segmentation for autonomous vehicles across various scenarios by actively controlling the gaze of the camera. The camera is mounted on a pan-tilt with two degrees of freedom as azimuth and elevation. The control of the azimuth is a follow-up PID control method mimicking the preview mechanism of human drivers. It is mainly used to improve the usefulness of the road segmentation in turning conditions. The control of the elevation is mainly used to improve the accuracy of the road segmentation in extreme external conditions, at the same time, taking into consideration of the usefulness. The elevation control method is inspired by the saccade-fixation mechanism of human eyes that scans the surrounding environment in the saccade mode and focuses on the object of interesting in the fixation mode. Similarly, the active camera will capture images of the current scene at different candidate elevations and select the optimal elevation. Experimental results demonstrate that the proposed active gaze control method effectively improves the performance of various road segmentation techniques under challenging conditions such as toward-light scenarios, U-turns, and low-speed situations.
Group behavior forecasting is an emergent re- search and application field in social computing. Most of the existing group behavior forecasting methods have heavily re- lied on structured data which is usually hard to...
详细信息
Group behavior forecasting is an emergent re- search and application field in social computing. Most of the existing group behavior forecasting methods have heavily re- lied on structured data which is usually hard to obtain. To ease the heavy reliance on structured data, in this paper, we pro- pose a computational approach based on the recognition of multiple plans/intentions underlying group behavior. We fur- ther conduct human experiment to empirically evaluate the effectiveness of our proposed approach.
DO we need a fundamental change in our professional culture and knowledge foundation for control and automation?If so,what are necessary and critical steps we must take to ensure such a change would take place effecti...
详细信息
DO we need a fundamental change in our professional culture and knowledge foundation for control and automation?If so,what are necessary and critical steps we must take to ensure such a change would take place effectively and efficiently,or more general,smoothly and sustainably?
Accurate detection of malignant transformation in oral potentially malignant disorders (OPMDs) is crucial for guiding effective treatment and improving patient management. This study evaluates the potential of MET- bi...
详细信息
Accurate detection of malignant transformation in oral potentially malignant disorders (OPMDs) is crucial for guiding effective treatment and improving patient management. This study evaluates the potential of MET- binding peptide-indocyanine green (cMBP-ICG), a mesenchymal-epithelial transition factor (MET)-targeted near-infrared fluorescence imaging (NIRFI) probe, for biopsy site selection in OPMDs. Preclinical results demonstrate the superior accuracy of NIRFI-assisted biopsy over conventional oral examination (COE)based biopsy in detecting high-grade dysplasia (HGD) or squamous cell carcinoma (SCC) and reducing missed detection rates. In a clinical trial with 50 patients, NIRFI-assisted biopsy achieves significantly higher diagnostic accuracy compared to COE-based biopsy (91% vs. 72%, p = 0.0005). These findings underscore the importance of NIRFI in enhancing diagnostic precision, supporting early detection and enabling timely and accurate treatment interventions for patients with OPMDs. The clinical trial is registered under the registration number ChiCTR2300074454.
View variation is a major challenge in face recognition. In this study, the authors propose a novel cross-view face recognition method by seeking potential intermediate domains between the source and target views to m...
详细信息
View variation is a major challenge in face recognition. In this study, the authors propose a novel cross-view face recognition method by seeking potential intermediate domains between the source and target views to model the connection of varying-views faces. Specifically, each intermediate domain is associated with a dictionary subspace. Learning proceeds in two phases. First, the authors discriminatively train a sub-dictionary for each subclass of data, which then compose a structured dictionary of powerful reconstructive and discriminative capability on the source data. Secondly, the authors gradually adapt the source domain dictionary to the target domain by incrementally reducing the reconstruction error on the target data, which forms a smooth transition path connecting the source and target domains. Instead of updating the structured dictionary integrally, the authors develop a refined sub-dictionary-based updating algorithm, which makes the intermediate dictionaries fit on the target data better and faster. Finally, the authors apply invariant sparse codes across the source, intermediate and target domains to render domain-shared representations, where the sample differences caused by view changes are reduced. Experiments on the CMU-PIE and Multi-PIE dataset demonstrate the effectiveness of the proposed method.
Recently, attributes have been introduced as a kind of high-level semantic information to help improve the classification accuracy. Multitask learning is an effective methodology to achieve this goal, which shares low...
详细信息
Recently, attributes have been introduced as a kind of high-level semantic information to help improve the classification accuracy. Multitask learning is an effective methodology to achieve this goal, which shares low-level features between attributes and actions. Yet such methods neglect the constraints that attributes impose on classes, which may fail to constrain the semantic relationship between the attributes and actions. In this paper, we explicitly consider such attribute-action relationship for human action recognition, and correspondingly, we modify the multitask learning model by adding attribute regularization. In this way, the learned model not only shares the low-level features, but also gets regularized according to the semantic constrains. In addition, since attribute and class label contain different amounts of semantic information, we separately treat attribute classifiers and action classifiers in the framework of multitask learning for further performance improvement. Our method is verified on three challenging datasets (KTH, UIUC, and Olympic Sports), and the experimental results demonstrate that our method achieves better results than that of previous methods on human action recognition.
Pooling strategies, such as max pooling and sum pooling, have been widely used to obtain the global representations for action videos. However, these pooling strategies have several disadvantages. First, they are easi...
详细信息
Pooling strategies, such as max pooling and sum pooling, have been widely used to obtain the global representations for action videos. However, these pooling strategies have several disadvantages. First, they are easily affected by unwanted background local features, the absence of discriminative local features and the times of actions periodically performed by actors. Second, most pooling strategies only use local features to build the global representation that captures little mid-level features for action representation. In this study, the authors propose a novel weighted pooling strategy based on actionlets representation for action recognition. The actionlets are defined as the movements of large bodies such as legs, arms and head, which capture rich mid-level features for action representation. Besides, the authors' method also incorporates the distribution information of actionlets into pooling procedure. Specifically, a pooling weight, which determines the importance of actionlet on the final video representation, is assigned to each actionlet. To learn the weight, they propose a novel discriminative learning algorithm to capture the discriminative information for pooling operation. They evaluate their weighted pooling on three datasets: KTH actions dataset, UCF sports dataset and Youtube actions dataset. Experimental results show the effectiveness of the proposed method.
In this paper, distributed containment control problems of general linear multi-agent systems are investigated. The objective is to make the followers in a multi-agent network converge to the convex hull spanned by so...
详细信息
In this paper, distributed containment control problems of general linear multi-agent systems are investigated. The objective is to make the followers in a multi-agent network converge to the convex hull spanned by some leaders whose control inputs are nonzero and not available to any *** mode surfaces are defined for the cases of reduced order and non-reduced order, respectively. For each case, fast sliding mode controllers are designed. It is shown that all the error trajectories exponentially reach the sliding mode surfaces in a finite time if for each follower, there exists at least one of the leaders who has a directed path to the follower, and the leaderscontrol inputs are bounded. The control Lyapunov function for exponential finite time stability, motivated by the fast terminal sliding mode control, is used to prove reachability of the sliding mode surfaces. Simulation examples are given to illustrate the theoretical results.
Ground-based cloud classification is challenging due to extreme variations in the appearance of clouds under different atmospheric conditions. Texture classification techniques have recently been introduced to deal wi...
详细信息
Ground-based cloud classification is challenging due to extreme variations in the appearance of clouds under different atmospheric conditions. Texture classification techniques have recently been introduced to deal with this issue. A novel texture descriptor, the salient local binary pattern (SLBP), is proposed for ground-based cloud classification. The SLBP takes advantage of the most frequently occurring patterns (the salient patterns) to capture descriptive information. This feature makes the SLBP robust to noise. Experimental results using ground-based cloud images demonstrate that the proposed method can achieve better results than current state-of-the-art methods.
Robots are changing our lives:sweeping robots patrol our living rooms; interactive robots accompany our children; industrial robots assemble vehicles; rescue robots search and save lives in catastrophes; medical robot...
详细信息
Robots are changing our lives:sweeping robots patrol our living rooms; interactive robots accompany our children; industrial robots assemble vehicles; rescue robots search and save lives in catastrophes; medical robots perform surgeries in *** better understand robots’challenges and impact, National Science Review (NSR) interviewed Professor Toshio Fukuda, who is one of the world’s most representative robotics experts and has developed a number of bionic robots and micro/nano-robots.
暂无评论