Search

With the advances in deep learning technology, Red Green Blue-Depth (RGB-D) Salient Object Detection (SOD) based on convolutional neural networks (CNNs) is gaining more and more attention. However, the accuracy of current models is challenging. It has been found that the quality of the depth features profoundly affects the accuracy. Several current RGB-D SOD techniques do not consider the quality of the depth features and directly fuse the original depth features and Red Green Blue (RGB) features for training, resulting in enhanced precision of the model. To address this issue, we propose a depth-quality purification feature processing network for RGB-D SOD, named DQPFPNet. First, we design a depth-quality purification feature processing (DQPFP) module to filter the depth features in a multi-scale manner and fuse them with RGB features in a multi-scale manner. This module can control and enhance the depth features explicitly in the process of cross-modal fusion, avoiding injecting noise or misleading depth features. Second, to prevent overfitting and avoid neuron inactivation, we utilize the RReLU activation function in the training process. In addition, we introduce the pixel position adaptive importance (PPAI) loss, which integrates local structure information to assign different weights to each pixel, thus better guiding the network's learning process and producing clearer details. Finally, a dual-stage decoder is designed to utilize contextual information to improve the modeling ability of the model and enhance the efficiency of the network. Extensive experiments on six RGB-D datasets demonstrate that DQPFPNet outperforms recent efficient models and delivers cutting-edge accuracy. [ABSTRACT FROM AUTHOR]

With the rapid development of neural networks in recent years, saliency detection based on deep learning has made great breakthroughs. Most deep saliency detection algorithms are based on convolutional neural networks, which still have great room for improvement in the edge accuracy of salient objects recognition, which may lead to fuzzy results in practical applications such as image matting. In order to improve the accuracy of detection, a saliency detection model based on semantic soft segmentation is proposed in this paper. Firstly, the semantic segmentation module combines spectral extinction and residual network model to obtain low-level color features and high-level semantic features, which can clearly segment all kinds of objects in the image. Then, the saliency detection module locates the position and contour of the main body of the object, and the edge accurate results are obtained after the processing of the two modules. Finally, compared with the other 11 algorithms on the DUTS-TEST data set, the weighted F-measure value of the proposed algorithm ranked first, which was 5.8% higher than the original saliency detection algorithm, and the accuracy was significantly improved. [ABSTRACT FROM AUTHOR]

Deep learning models have become the mainstream algorithm for processing computer vision tasks. In the tasks of object detection, the detection box is usually set as a rectangular box aligned with the coordinate axis, so as to achieve the complete packaging of the object. However, when facing some objects with large aspect ratio and angle, the bounding box must be enlarged, which makes the bounding box contain a large amount of useless background information. In this study, a different approach based on YOLOv5 is adopted. By this means, the angle information dimension is added at the head, and angle regression is also added at the same time of the boundary regression. Then the loss of the boundary box is calculated by combining ciou and smoothl1, so that the obtained boundary box is more closely suitable for the actual object. At the same time, the original dataset tags are also pre-processed to calculate the angle information of interest. The purpose of these improvements is to realize object detection with angles in remote-sensing images, especially for objects with large aspect ratios, such as ships, airplanes, and automobiles. Compared with the traditional and other state-of-the-art arbitrarily oriented object detection model based on deep learning, experimental results show that the proposed method has a unique effect in detecting rotating objects. [ABSTRACT FROM AUTHOR]

Object tracking has been a challenge in computer vision. In this paper, we present a novel method to model target appearance and combine it with structured output learning for robust online tracking within a tracking-by-detection framework. We take both convolutional features and handcrafted features into account to robustly encode the target appearance. First, we extract convolutional features of the target by kernels generated from the initial annotated frame. To capture appearance variation during tracking, we propose a new strategy to update the target and background kernel pool. Secondly, we employ a structured output SVM for refining the target's location to mitigate uncertainty in labeling samples as positive or negative. Compared with existing state-of-the-art trackers, our tracking method not only enhances the robustness of the feature representation, but also uses structured output prediction to avoid relying on heuristic intermediate steps to produce labelled binary samples. Extensive experimental evaluation on the challenging OTB-50 video sequences shows competitive results in terms of both success and precision rate, demonstrating the merits of the proposed tracking method. [ABSTRACT FROM AUTHOR]