Past work on object detection has emphasized the issues of feature extraction and classification, however, relatively less attention has been given to the critical issue of feature selection. The main trend in feature extraction has been representing the data in a lower dimensional space, for example, using principal component analysis (PCA). Without using an effective scheme to select an appropriate set of features in this space, however, these methods rely mostly on powerful classification algorithms to deal with redundant and irrelevant features. In this paper, we argue that feature selection is an important problem in object detection and demonstrate that genetic algorithms (GAs) provide a simple, general, and powerful framework for selecting good subsets of features, leading to improved detection rates. As a case study, we have considered PCA for feature extraction and support vector machines (SVMs) for classification. The goal is searching the PCA space using GAs to select a subset of eigenvectors encoding important information about the target concept of interest. This is in contrast to traditional methods selecting some percentage of the top eigenvectors to represent the target concept, independently of the classification task. We have tested the proposed framework on two challenging applications: vehicle detection and face detection. Our experimental results illustrate significant performance improvements in both cases. 相似文献
Soft materials that can reversibly transform shape in response to moisture have applications in diverse areas such as soft robotics and biomedicine. However, the design of a structurally transformable or mechanically self‐healing version of such a humidity‐responsive material, which can arbitrarily change shape and reconfigure its 3D structures remains challenging. Here, by drawing inspiration from a covalent–noncovalent network, an elaborately designed biopolyester is developed that features a simple hygroscopic actuation mechanism, straightforward manufacturability at low ambient temperature (≤35 °C), fast and stable response, robust mechanical properties, and excellent self‐healing ability. Diverse functions derived from various 3D shapes that can grasp, swing, close–open, lift, or transport an object are further demonstrated. This strategy of easy‐to‐process 3D structured self‐healing actuators is expected to combine with other actuation mechanisms to extend new possibilities in diverse practical applications. 相似文献
It is a challenge to manufacture pressure‐sensing materials that possess flexibility, high sensitivity, large‐area compliance, and capability to detect both tiny and large motions for the development of artificial intelligence products. Herein, a very simple and low‐cost approach is proposed to fabricate versatile pressure sensors based on microcrack‐designed carbon black (CB)@polyurethane (PU) sponges via natural polymer‐mediated water‐based layer‐by‐layer assembly. These sensors are capable of satisfying the requirements of ultrasmall as well as large motion monitoring. The versatility of these sensors benefits from two aspects: microcrack junction sensing mechanism for tiny motion detecting (91 Pa pressure, 0.2% strain) inspired by the spider sensory system and compressive contact of CB@PU conductive backbones for large motion monitoring (16.4 kPa pressure, 60% strain). Furthermore, these sensors exhibit excellent flexibility, fast response times (<20 ms), as well as good reproducibility over 50 000 cycles. This study also demonstrates the versatility of these sensors for various applications, ranging from speech recognition, health monitoring, bodily motion detection to artificial electronic skin. The desirable comprehensive performance of our sensors, which is comparable to the recently reported pressure‐sensing devices, together with their significant advantages of low‐cost, easy fabrication, especially versatility, makes them attractive in the future of artificial intelligence. 相似文献
Cross-modal retrieval aims to retrieve related items across different modalities, for example, using an image query to retrieve related text. The existing deep methods ignore both the intra-modal and inter-modal intra-class low-rank structures when fusing various modalities, which decreases the retrieval performance. In this paper, two deep models (denoted as ILCMR and Semi-ILCMR) based on intra-class low-rank regularization are proposed for supervised and semi-supervised cross-modal retrieval, respectively. Specifically, ILCMR integrates the image network and text network into a unified framework to learn a common feature space by imposing three regularization terms to fuse the cross-modal data. First, to align them in the label space, we utilize semantic consistency regularization to convert the data representations to probability distributions over the classes. Second, we introduce an intra-modal low-rank regularization, which encourages the intra-class samples that originate from the same space to be more relevant in the common feature space. Third, an inter-modal low-rank regularization is applied to reduce the cross-modal discrepancy. To enable the low-rank regularization to be optimized using automatic gradients during network back-propagation, we propose the rank-r approximation and specify the explicit gradients for theoretical completeness. In addition to the three regularization terms that rely on label information incorporated by ILCMR, we propose Semi-ILCMR in the semi-supervised regime, which introduces a low-rank constraint before projecting the general representations into the common feature space. Extensive experiments on four public cross-modal datasets demonstrate the superiority of ILCMR and Semi-ILCMR over other state-of-the-art methods.
Developing on-board automotive driver assistance systems aiming to alert drivers about driving environments, and possible collision with other vehicles has attracted a lot of attention lately. In these systems, robust and reliable vehicle detection is a critical step. This paper presents a review of recent vision-based on-road vehicle detection systems. Our focus is on systems where the camera is mounted on the vehicle rather than being fixed such as in traffic/driveway monitoring systems. First, we discuss the problem of on-road vehicle detection using optical sensors followed by a brief review of intelligent vehicle research worldwide. Then, we discuss active and passive sensors to set the stage for vision-based vehicle detection. Methods aiming to quickly hypothesize the location of vehicles in an image as well as to verify the hypothesized locations are reviewed next. Integrating detection with tracking is also reviewed to illustrate the benefits of exploiting temporal continuity for vehicle detection. Finally, we present a critical overview of the methods discussed, we assess their potential for future deployment, and we present directions for future research. 相似文献