Shouhong Wan

An approach for image retrieval based on visual saliency

Considering the gap between low-level image features and the high-level semantic concept in content-based image retrieval (CBIR), a new approach is proposed for image retrieval based on visual saliency, by analyzing the human visual perception process. Visual information is introduced as the new feature which reflects high-level semantic concept objectively. First, the visual saliency model for image retrieval is established. The saliency features of intensity, color and texture are calculated. Second, integrated global saliency map is synthesized and its statistic histogram is used as a new feature in image retrieval. Finally, the similarity of color images is computed by combining the color feature and the histogram of integrated saliency map. Results of experiments show that our approach improves retrieval precision and recall when compared with the classical color feature approach.

Sparsest Random Scheduling for Compressive Data Gathering in Wireless Sensor Networks

Compressive sensing (CS)-based in-network data processing is a promising approach to reduce packet transmission in wireless sensor networks. Existing CS-based data gathering methods require a large number of sensors involved in each CS measurement gathering, leading to the relatively high data transmission cost. In this paper, we propose a sparsest random scheduling for compressive data gathering scheme, which decreases each measurement transmission cost from O(N) to O(log(N)) without increasing the number of CS measurements as well. In our scheme, we present a sparsest measurement matrix, where each row has only one nonzero entry. To satisfy the restricted isometric property, we propose a design method for representation basis, which is properly generated according to the sparsest measurement matrix and sensory data. With extensive experiments over real sensory data of CitySee, we demonstrate that our scheme can recover the real sensory data accurately. Surprisingly, our scheme outperforms the dense measurement matrix with a discrete cosine transformation basis over 5 dB on data recovery quality. Simulation results also show that our scheme reduces almost 10 × energy consumption compared with the dense measurement matrix for CS-based data gathering.

A Novel Approach for Change Detection in Remote Sensing Image Based on Saliency Map

Detecting change of remote sensing images is very important for some applications such as tracking of moving objects and motion estimation. Traditional work on change detection has largely been based on segmentation approaches of a single feature. It excessively depends on the threshold of the single feature to determine whether the change of spectral information is caused by the change of object. The results of traditional change detection approaches can easily be affected by noise, blur, contrast level and brightness level. To overcome the deficiency, we improve the Itti visual saliency model and propose an effective and robust approach based on saliency map to detect real changed regions between two remote sensing images of a given scene acquired at different times. The results of the experiments indicate that our approach is very robust to noise, contrast level and brightness level.

A Novel Algorithm for Ship Detection Based on Dynamic Fusion Model of Multi-feature and Support Vector Machine

Ship detection is one of the most important applications of target recognition based on optical remote sensing images. In this paper, we propose an uncertain ship target extraction algorithm based on dynamic fusion model of multi-feature and variance feature of optical remote sensing image. We choose several geometrical features, such as length, wide, rectangular ratio, tightness ratio and so on, using SVM to train and predict the uncertain ship targets extracted by our algorithm automatically. Experiments show that our algorithm is very robust, and the recognition rate of our algorithm can reach or even better than 95%, with the false alarm rate is kept at 3%.

IndoorSTG: A Flexible Tool to Generate Trajectory Data for Indoor Moving Objects

Indoor moving objects management has been a research focus in recent years. In order to get the trajectory data of indoor moving objects, people have to deploy a lot of positioning equipment, such as RFID readers and tags, which takes lots of money, time, and other costs. In addition, it is a very complex and costly process to construct different environment settings for various indoor applications. Aiming to provide experimental trajectory data for various indoor operations and mining algorithms, in this paper we present a flexible tool to generate trajectories for indoor moving objects, which is named IndoorSTG (Indoor Spatiotemporal Trajectory Generator). IndoorSTG can simulate different indoor environments using various elements including rooms, doors, corridors, stairs, elevators, and virtual positioning devices such as RFID or Bluetooth readers. Meanwhile, it can generate semantic-based trajectories for indoor moving objects in a specific indoor space. After an overview of the general features of IndoorSTG, we discuss the architecture and implementation of IndoorSTG. And finally, a case study of IndoorSTGs demonstration is presented.

Multi-Scale Local Spatial Binary Patterns for Content-Based Image Retrieval

Content-based image retrieval (CBIR) has been widely studied in recent years. CBIR usually employs feature descriptors to describe the concerned characters of images, such as geometric descriptor and texture descriptor. Many texture descriptors in texture analysis and image retrieval are based on the so-called Local Binary Pattern (LBP) technique. However, LBP lacks of the spatial distribution information of texture features. In this paper, we aim at improving the traditional LBP and present a novel texture feature descriptor for CBIR called Multi-Scale Local Spatial Binary Patterns (MLSBP). MLSBP integrates LBP with spatial distribution information of gray-level variation direction and gray-level variation between the referenced pixel and its neighbors. In addition, MLSBP extracts the texture features from images on different scale levels. We conduct experiments to compare the performance of MLSBP with five competitors including LBP, Uniform LBP (ULBP), Completed LBP (CLBP), Local Ternary Patterns (LTP), and Local Tetra Patterns (LTrP). Also three benchmark image databases are used in the measurement, which are the Bradotz Texture Database (DB1), the MIT VisTex Database (DB2), and the Corel 1000 Database (DB3). The experimental results show that MLSBP is superior to the competitive algorithms in terms of precision and recall.

An Effective Image Retrieval Technique Based on Color Perception

In content-based image retrieval (CBIR), color is the most intuitive image features and it is widely used. But The current color feature can describe the semantics of the whole image effectively, but does not reflect characteristics of the color salience objects in an image. For the purpose of giving prominence to the color characteristics of salience objects, this paper proposes a new color feature descriptor based on color visual perception model. By analyzing the human color visual perception process, the color perception model is proposed at first. This model integrates the intensity, the color contrast and self saliency, sparsity and centricity saliency to describe human color visual perception of the image. Then, the new color feature descriptor is calculated by weighting the significant bit-plane histograms with color perception map. Finally, similarity measure is presented for the new color feature. Experiment results show that the proposed color feature is more accurate and efficient in retrieving images with user-interested color objects. Compared with the other three retrieval methods, the proposed technique improves the retrieval accuracy effectively.

Local spatial binary pattern: a new feature descriptor for content-based image retrieval

In this paper, we propose a novel image retrieval algorithm using local spatial binary patterns (LSBP) for contentbased image retrieval. The traditional local binary pattern (LBP) encodes the relationship between the referenced pixel and its surrounding neighbors by calculating gray-level difference, but LBP lacks the spatial distribution information of texture direction. The proposed method encodes spatial relationship of the referenced pixel and its neighbors, based on the gray-level variation patterns of the horizontal, vertical and oblique directions. Additionally, variation between center pixel and its surrounding neighbors is calculated to reflect the magnitude information of the whole image. We compare our method with LBP, uniform LBP (ULBP), completed LBP (CLBP), local ternary pattern (LTP) and local tetra patterns (LTrP) based on three benchmark image databases including, Brodatz texture database(DB1), Corel database(DB2), and MIT VisTex database(DB3). Experiment analysis shows that the proposed method improves the retrieval results from 70.49%/41.30% to 73.26%/46.26% in terms of average precision/average recall on database DB2, from 79.02% to 85.92% and 82.14% to 90.88% in terms of average precision on databases DB1 and DB3, respectively, as compared with the traditional LBP.

HB-Storage: Optimizing SSDs with a HDD Write Buffer

In recent years, flash memory based storage device SSDs (solid state drives) have been regarded as the storage devices of next generation to replace HDDs (hard disk drivers). However, the high price of SSDs, especially those with high performance, results in the situation that SSDs and HDDS are both popularly used in real applications. In order to integrate the merits of SSDs and HDDS, it has become a hot research topic that using HDDs for SSDs to construct a hybrid storage system. The goal of this paper is to use the cheap low-end SSD and HDD to build a hybrid storage system with high efficiency, which is called HB-Storage. HB-Storage considers the characters of SSDs and HDDs, and builds a HDD write buffer to optimize the SSD write request. The write buffer is designed based on the data access load statistics. As a consequence, HB-Storage can utilize the higher read performance of SSDs, and can also improve the random write latency of SSDs. The experimental results show that HB-Storage can maintain a high read performance and significantly reduce the write requests on the SSD, and thus has higher overall performance.

A New Texture Direction Feature Descriptor and Its Application in Content-Based Image Retrieval

Local Binary Pattern (LBP) has been widely used in texture analysis and content-based image retrieval (CBIR). LBP encodes the relationship between the referenced pixel and its surrounding neighbors by computing gray-level variation. However, LBP is unable to reflect the spatial distribution information of gray variation direction in the whole image. Therefore, in this paper, we propose a new texture direction feature descriptor to extract the spatial distribution information of gray-level variation between pixels. After the calculation of the gray variation pattern on different directions, we construct the statistic histograms of pattern pairs between the referenced pixel and its neighbor pixels. The performance of the proposed feature descriptor is compared with different methods using two benchmark image databases. Performance analysis shows that the proposed feature descriptor improves the retrieval precision rate, as well as the recall rate both in texture and natural scene images.