Specificity-preserving RGB-D saliency detection

Salient object detection(SOD)in RGB and depth images has attracted increasing research interest.Existing RGB-D SOD models usually adopt fusion strategies to learn a shared representation from RGB and depth modalities,while few methods explicitly consider how to preserve modality-specific characteristics.In this study,we propose a novel framework,the specificity-preserving network(SPNet),which improves SOD performance by exploring both the shared information and modality-specific properties.Specifically,we use two modality-specific networks and a shared learning network to generate individual and shared saliency prediction maps.To effectively fuse cross-modal features in the shared learning network,we propose a cross-enhanced integration module(CIM)and propagate the fused feature to the next layer to integrate cross-level information.Moreover,to capture rich complementary multi-modal information to boost SOD performance,we use a multi-modal feature aggregation(MFA)module to integrate the modalityspecific features from each individual decoder into the shared decoder.By using skip connections between encoder and decoder layers,hierarchical features can be fully combined.Extensive experiments demonstrate that our SPNet outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection benchmarks.The project is publicly available at https://github.com/taozh2017/SPNet.

Hierarchical Visual Attention Model for Saliency Detection Inspired by Avian Visual Pathways

Visual attention is a mechanism that enables the visual system to detect potentially important objects in complex environment. Most computational visual attention models are designed with inspirations from mammalian visual systems.However, electrophysiological and behavioral evidences indicate that avian species are animals with high visual capability that can process complex information accurately in real time. Therefore,the visual system of the avian species, especially the nuclei related to the visual attention mechanism, are investigated in this paper. Afterwards, a hierarchical visual attention model is proposed for saliency detection. The optic tectum neuron responses are computed and the self-information is used to compute primary saliency maps in the first hierarchy. The "winner-takeall" network in the tecto-isthmal projection is simulated and final saliency maps are estimated with the regularized random walks ranking in the second hierarchy. Comparison results verify that the proposed model, which can define the focus of attention accurately, outperforms several state-of-the-art models.This study provides insights into the relationship between the visual attention mechanism and the avian visual pathways. The computational visual attention model may reveal the underlying neural mechanism of the nuclei for biological visual attention.

Saliency detection and edge feature matching approach for crater extraction

Craters are salient terrain features on planetary surfaces, and provide useful information about the relative dating of geological unit of planets. In addition, they are ideal landmarks for spacecraft navigation. Due to low contrast and uneven illumination, automatic extraction of craters remains a challenging task. This paper presents a saliency detection method for crater edges and a feature matching algorithm based on edges informa- tion. The craters are extracted through saliency edges detection, edge extraction and selection, feature matching of the same crater edges and robust ellipse fitting. In the edges matching algorithm, a crater feature model is proposed by analyzing the relationship between highlight region edges and shadow region ones. Then, crater edges are paired through the effective matching algorithm. Experiments of real planetary images show that the proposed approach is robust to different lights and topographies, and the detection rate is larger than 90%.

Saliency detection based on superpixels clustering and stereo disparity

Reliable saliency detection can be used to quickly and effectively locate objects in images. In this paper, a novel algorithm for saliency detection based on superpixels clustering and stereo disparity （SDC） is proposed. Firstly, we use an improved superpixels clustering method to decompose the given image. Then, the disparity of each superpixel is computed by a modified stereo correspondence algorithm. Finally, a new measure which combines stereo disparity with color contrast and spatial coherence is defined to evaluate the saliency of each superpixel. From the experiments we can see that regions with high disparity can get higher saliency value, and the saliency maps have the same resolution with the source images, objects in the map have clear boundaries. Due to the use of superpixel and stereo disparity information, the proposed method is computationally efficient and outperforms some state-of-the-art color- based saliency detection methods.

Method for pests detecting in stored grain based on spectral residual saliency edge detection

Pests detecting is an important research subject in grain storage field.In the past decades,many edge detection methods have been applied to the edge detection of stored grain pests.Although some of them can realize the stored grain pests detecting,precision and robustness are not good enough.Spectral residual(SR)saliency edge detection defines the logarithmic spectrumof image as novelty part of the image information.The remaining spectrumis converted to the airspace to obtain edge detection results.SR algorithm is completely based on frequency domain processing.It not only can effectively simplify the target detection algorithm,but also can improve the effectiveness of target recognition.The experimental results show that the edge results of stored grain pests detected by SR method are effective and stable.

Vehicle Detection Based on Visual Saliency and Deep Sparse Convolution Hierarchical Model

Traditional vehicle detection algorithms use traverse search based vehicle candidate generation and hand crafted based classifier training for vehicle candidate verification.These types of methods generally have high processing times and low vehicle detection performance.To address this issue,a visual saliency and deep sparse convolution hierarchical model based vehicle detection algorithm is proposed.A visual saliency calculation is firstly used to generate a small vehicle candidate area.The vehicle candidate sub images are then loaded into a sparse deep convolution hierarchical model with an SVM-based classifier to perform the final detection.The experimental results demonstrate that the proposed method is with 94.81% correct rate and 0.78% false detection rate on the existing datasets and the real road pictures captured by our group,which outperforms the existing state-of-the-art algorithms.More importantly,high discriminative multi-scale features are generated by deep sparse convolution network which has broad application prospects in target recognition in the field of intelligent vehicle.

Saliency detection of infrared image based on region covariance and global feature

In order to better represent infrared target features under different environments, a saliency detection method based on region covariance and global feature is proposed. Firstly, the region covariance features on different scale spaces and different image regions are extracted and transformed into sigma features,then combined with central position feature, the local salient map is generated. Next, a global salient map is generated by gray contrast and density estimation. Finally, the saliency detection result of infrared images is obtained by fusing the local and global salient maps. The experimental results show that the salient map of the proposed method has complete target features and obvious edges,and the proposed method is better than the state of art method both qualitatively and quantitatively.

Visual Attention Modeling in Compressed Domain:From Image Saliency Detection to Video Saliency Detection

Saliency detection models, which are used to extract salient regions in visual scenes, are widely used in various multimedia processing applications. It has attracted much attention in the area of computer vision over the past decades. Since most images or videos over the Internet are stored in compressed domains such as images in JPEG format and videos in MPEG2 format, H.264 format, and MPEG4 Visual format, many saliency detection models have been proposed in the compressed domain recently. We provide a review of our works on saliency detection models in the compressed domain in this paper.Besides, we introduce some commonly used fusion strategies to combine spatial saliency map and temporal saliency map to compute the final video saliency map.

Enhanced Object Detection and Classification via Multi-Method Fusion

Advances in machine vision systems have revolutionized applications such as autonomous driving,robotic navigation,and augmented reality.Despite substantial progress,challenges persist,including dynamic backgrounds,occlusion,and limited labeled data.To address these challenges,we introduce a comprehensive methodology toenhance image classification and object detection accuracy.The proposed approach involves the integration ofmultiple methods in a complementary way.The process commences with the application of Gaussian filters tomitigate the impact of noise interference.These images are then processed for segmentation using Fuzzy C-Meanssegmentation in parallel with saliency mapping techniques to find the most prominent regions.The Binary RobustIndependent Elementary Features(BRIEF)characteristics are then extracted fromdata derived fromsaliency mapsand segmented images.For precise object separation,Oriented FAST and Rotated BRIEF(ORB)algorithms areemployed.Genetic Algorithms(GAs)are used to optimize Random Forest classifier parameters which lead toimproved performance.Our method stands out due to its comprehensive approach,adeptly addressing challengessuch as changing backdrops,occlusion,and limited labeled data concurrently.A significant enhancement hasbeen achieved by integrating Genetic Algorithms(GAs)to precisely optimize parameters.This minor adjustmentnot only boosts the uniqueness of our system but also amplifies its overall efficacy.The proposed methodologyhas demonstrated notable classification accuracies of 90.9%and 89.0%on the challenging Corel-1k and MSRCdatasets,respectively.Furthermore,detection accuracies of 87.2%and 86.6%have been attained.Although ourmethod performed well in both datasets it may face difficulties in real-world data especially where datasets havehighly complex backgrounds.Despite these limitations,GAintegration for parameter optimization shows a notablestrength in enhancing the overall adaptability and performance of our system.

Co-salient object detection with iterative purification and predictive optimization

Background Co-salient object detection(Co-SOD)aims to identify and segment commonly salient objects in a set of related images.However,most current Co-SOD methods encounter issues with the inclusion of irrelevant information in the co-representation.These issues hamper their ability to locate co-salient objects and significantly restrict the accuracy of detection.Methods To address this issue,this study introduces a novel Co-SOD method with iterative purification and predictive optimization(IPPO)comprising a common salient purification module(CSPM),predictive optimizing module(POM),and diminishing mixed enhancement block(DMEB).Results These components are designed to explore noise-free joint representations,assist the model in enhancing the quality of the final prediction results,and significantly improve the performance of the Co-SOD algorithm.Furthermore,through a comprehensive evaluation of IPPO and state-of-the-art algorithms focusing on the roles of CSPM,POM,and DMEB,our experiments confirmed that these components are pivotal in enhancing the performance of the model,substantiating the significant advancements of our method over existing benchmarks.Experiments on several challenging benchmark co-saliency datasets demonstrate that the proposed IPPO achieves state-of-the-art performance.

An Application of RGBD-Based Skeleton Reconstruction for Pedestrian Detection and Occlusion Handling

This study explores the challenges posed by pedestrian detection and occlusion in AR applications, employing a novel approach that utilizes RGB-D-based skeleton reconstruction to reduce the overhead of classical pedestrian detection algorithms during training. Furthermore, it is dedicated to addressing occlusion issues in pedestrian detection by using Azure Kinect for body tracking and integrating a robust occlusion management algorithm, significantly enhancing detection efficiency. In experiments, an average latency of 204 milliseconds was measured, and the detection accuracy reached an outstanding level of 97%. Additionally, this approach has been successfully applied in creating a simple yet captivating augmented reality game, demonstrating the practical application of the algorithm.

Robust detection algorithm with triple constraints for cooperative target based on spectral residual

The accurate detection of cooperative targets plays a key and foundational role in unmanned aerial vehicle (UAV) landing autonomously. The standard method based on fixed threshold is too susceptible to both illumination variations and interference. To overcome issues above, a robust detection algorithm with triple constraints for cooperative targets based on spectral residual (TCSR) is proposed. Firstly, by designing an asymmetric cooperative target, which comprises red background, green H and triangle target, the captured original image is converted into a Lab color space, whose saliency map is yielded by constructing the spectral residual. Then, the triple constraints are developed according to the prior knowledge of the cooperative target. Finally, the salient region in saliency map is considered as the cooperative target, and it meets the triple constraints. Experimental results in complex environments show that the proposed TCSR outperforms the standard methods in higher detection accuracy and lower false alarm rate.

Real-time object segmentation based on convolutional neural network with saliency optimization for picking

This paper concerns the problem of object segmentation in real-time for picking system. A region proposal method inspired by human glance based on the convolutional neural network is proposed to select promising regions, allowing more processing is reserved only for these regions. The speed of object segmentation is significantly improved by the region proposal method.By the combination of the region proposal method based on the convolutional neural network and superpixel method, the category and location information can be used to segment objects and image redundancy is significantly reduced. The processing time is reduced considerably by this to achieve the real time. Experiments show that the proposed method can segment the interested target object in real time on an ordinary laptop.

A Saliency Based Image Fusion Framework for Skin Lesion Segmentation and Classification

Melanoma,due to its higher mortality rate,is considered as one of the most pernicious types of skin cancers,mostly affecting the white populations.It has been reported a number of times and is now widely accepted,that early detection of melanoma increases the chances of the subject’s survival.Computer-aided diagnostic systems help the experts in diagnosing the skin lesion at earlier stages using machine learning techniques.In thiswork,we propose a framework that accurately segments,and later classifies,the lesion using improved image segmentation and fusion methods.The proposed technique takes an image and passes it through two methods simultaneously;one is the weighted visual saliency-based method,and the second is improved HDCT based saliency estimation.The resultant image maps are later fused using the proposed image fusion technique to generate a localized lesion region.The resultant binary image is later mapped back to the RGB image and fed into the Inception-ResNet-V2 pre-trained model-trained by applying transfer learning.The simulation results show improved performance compared to several existing methods.

采用Ranking Saliency算法改进的交通标志检测方法

目的:交通标志的检测是车载辅助系统的关键环节之一,针对YOLO V3检测算法得到的检测结果存在目标框不精确的问题,提出改进交通标志目标检测算法。方法:YOLO V3是当前目标检测算法中检测召回率高且速度较优的算法,但在定位上不够准确。为解决该问题,本文采用流行排序算法对得到的检测框进行二次修正,从而使得目标定位精度提升。结果:通过结合YOLO V3和流行排序算法使目标检测框的交并比提升了3%~9%。结论:通过YOLO V3和Ranking Saliency的结合能够使得目标检测的定位精度提高。

RGBD Salient Object Detection by Structured Low-Rank Matrix Recovery and Laplacian Constraint

A structured low-rank matrix recovery model for RGBD salient object detection is proposed. Firstly, the problem is described by a low-rank matrix recovery, and the hierarchical structure of RGB image is added to the sparsity term. Secondly, the depth information is fused into the model by a Laplacian regularization term to ensure that the image regions which share similar depth value will be allocated to similar saliency value. Thirdly, a variation of alternating direction method is proposed to solve the proposed model. Finally, both quantitative and qualitative experimental results on NLPR1000 and NJU400 show the advantage of the proposed RGBD salient object detection model. © 2017, Tianjin University and Springer-Verlag Berlin Heidelberg.

Cluster-Based Saliency-Guided Content-Aware Image Retargeting

Straightforward image resizing operators without considering image contents （e.g., uniform scaling） cannot usually produce satisfactory results, while content-aware image retargeting aims to arbitrarily change image size while preserving visually prominent features. In this paper, a cluster-based saliency-guided seam carving algorithm for content- aware image retargeting is proposed. To cope with the main drawback of the original seam carving algorithm relying on only gradient-based image importance map, we integrate a gradient-based map and a cluster-based saliency map to generate a more reliable importance map, resulting in better single image retargeting results. Experimental results have demonstrated the efficacy of the proposed algorithm.

A Detection Method of Bolts on Axlebox Cover Based on Cascade Deep Convolutional Neural Network

This paper proposes a cascade deep convolutional neural network to address the loosening detection problem of bolts on axlebox covers.Firstly,an SSD network based on ResNet50 and CBAM module by improving bolt image features is proposed for locating bolts on axlebox covers.And then,theA2-PFN is proposed according to the slender features of the marker lines for extracting more accurate marker lines regions of the bolts.Finally,a rectangular approximationmethod is proposed to regularize themarker line regions asaway tocalculate the angle of themarker line and plot all the angle values into an angle table,according to which the criteria of the angle table can determine whether the bolt with the marker line is in danger of loosening.Meanwhile,our improved algorithm is compared with the pre-improved algorithmin the object localization stage.The results show that our proposed method has a significant improvement in both detection accuracy and detection speed,where ourmAP(IoU=0.75)reaches 0.77 and fps reaches 16.6.And in the saliency detection stage,after qualitative comparison and quantitative comparison,our method significantly outperforms other state-of-the-art methods,where our MAE reaches 0.092,F-measure reaches 0.948 and AUC reaches 0.943.Ultimately,according to the angle table,out of 676 bolt samples,a total of 60 bolts are loose,69 bolts are at risk of loosening,and 547 bolts are tightened.

Thermal Infrared Salient Human Detection Model Combined with Thermal Features in Airport Terminal

Target detection in low light background is one of the main tasks of night patrol robots for airport terminal.However,if some algorithms can run on a robot platform with limited computing resources,it is difficult for these algorithms to ensure the detection accuracy of human body in the airport terminal. A novel thermal infrared salient human detection model combined with thermal features called TFSHD is proposed. The TFSHD model is still based on U-Net,but the decoder module structure and model lightweight have been redesigned. In order to improve the detection accuracy of the algorithm in complex scenes,a fusion module composed of thermal branch and saliency branch is added to the decoder of the TFSHD model. Furthermore,a predictive loss function that is more sensitive to high temperature regions of the image is designed. Additionally,for the sake of reducing the computing resource requirements of the algorithm,a model lightweight scheme that includes simplifying the encoder network structure and controlling the number of decoder channels is adopted. The experimental results on four data sets show that the proposed method can not only ensure high detection accuracy and robustness of the algorithm,but also meet the needs of real-time detection of patrol robots with detection speed above 40 f/s.