A learning-based multibranch deep probability network is proposed to estimate the illuminated color of the light source in a scene, commonly referred to as color constancy. The method consists of two coupled subnetworks, which are the deep multibranch illumination estimating network (DMBEN) and deep probability computing network (DPN). The one branch of DMBEN estimates the global illuminant through pooling layer and fully connected layer, whereas the other branch is built as an end-to-end residuals network (Res-net) to evaluate the local illumination. The other adjoint subnetwork DPN separately computes the probabilities that results of DMBEN are similar to the ground truth, then determines the better estimation according to the two probabilities under a new criterion. The results of extensive experiments on Color Checker and NUS 8-Camera datasets show that the proposed approach is superior to the state-of-the-art methods both in efficiency and effectiveness.
Along with the rapid development of the unmanned aerial vehicle technology, multiple vehicle tracking (MVT) in aerial video sequence has received widespread interest for providing the required traffic information. Due to the camera motion and complex background, MVT in aerial video sequence poses unique challenges. We propose an efficient MVT algorithm via driver behavior-based Kalman filter (DBKF) and an improved deterministic data association (IDDA) method. First, a hierarchical image registration method is put forward to compensate the camera motion. Afterward, to improve the accuracy of the state estimation, we propose the DBKF module by incorporating the driver behavior into the Kalman filter, where artificial potential field is introduced to reflect the driver behavior. Then, to implement the data association, a local optimization method is designed instead of global optimization. By introducing the adaptive operating strategy, the proposed IDDA method can also deal with the situation in which the vehicles suddenly appear or disappear. Finally, comprehensive experiments on the DARPA VIVID data set and KIT AIS data set demonstrate that the proposed algorithm can generate satisfactory and superior results.
KEYWORDS: RGB color model, Visualization, Magnetic resonance imaging, Image segmentation, Visual process modeling, Lithium, Information visualization, Detection and tracking algorithms, Space operations, Image fusion
Background prior selection is the key step in current ranking-based saliency detection approaches. The existing related methods usually choose boundary regions of an image or the region with low initial saliency value in single image scale as the background. Then, the saliency map is obtained by ranking the inside similarity and correlation. However, these methods cannot handle situations in which the salient object lies on the image boundary (boundary-salient) multiple salient objects exist in a single image (multisalient). To this end, this paper proposes an adaptive background selection method by exploiting the background invariance in different image scales within distinct color spaces. Through embedding the selected background prior into multiple newly proposed ranking-based saliency methods, the superiority of the obtained background prior is strongly verified. Exhaustive experiments on four challenging datasets demonstrate that the proposed method outperforms the state-of-the-art methods in handling the boundary-salient and multisalient situations.
Vehicle detection in high-resolution aerial images has received widespread interests when it comes to providing the required information for traffic management and urban planning. It is challenging due to the relatively small size of the vehicles and the complex background. Furthermore, it is particularly challenging if the higher detection efficiency is required. Therefore, an urban vehicle detection algorithm is proposed via improved entropy rate clustering (IERC) and correlation-based sequential dictionary learning (CSDL). First, to enhance the detection accuracy, IERC is designed to generate more regular superpixels. It aims to avoid the situation that one superpixel sometimes straddles multiple vehicles. The generated superpixels are then treated as the seeds for the training sample selection. Then, CSDL is constructed to achieve a fast sequential training and updating of the dictionary. In CSDL, only the atoms correlated with the sparse representation of the new training data are inferred. Finally, comprehensive analyses and comparisons on two data sets demonstrate that the proposed method generates satisfactory and competitive results.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.