Local Difference Binary Research Articles

ESA-VLAD: A Lightweight Network Based on Second-Order Attention and NetVLAD for Loop Closure Detection

Loop closure detection (LCD) is an important portion of Simultaneous Localization and Mapping (SLAM) because of its ability to reduce accumulated position errors. In this letter, we propose a novel loop closure detection algorithm named ESA-VLAD. The crucial part of ESA-VLAD is a redesigned network with EfficientNetB0 as backbone for extracting global features, which integrates a second-order attention module in order to effectively learn the correlations between features within the feature map. A trainable Vector of Local Aggregated Descriptors (NetVLAD) is integrated in the last layer of the network to generate a compact and fixed-length global feature. Knowledge distillation strategy is adopted in training of the proposed network to accelerate the training process. For the global features, Hierarchical Navigable Small World (HNSW) is employed to retrieve the loop closure candidate images. In addition, an efficient geometrical consistency check based on local difference binary (LDB) descriptors is designed to verify loop closure matches. Experiments on several public datasets demonstrate that ESA-VLAD can obtain higher recall rates under 100% precision and less processing time per frame compared to other typical and state-of-the-art methods.

Video Forgery Detection Method based on Local Difference Binary

Recently, the rapid development of video editing software has made video forgery applicable. Researchers have proposed methods to detect forged video frames. These methods utilize codec properties, motion artifacts, noise effect and frame similarity to detect forgery. Execution time and low detection accuracy are the two main drawbacks of forgery detection methods reported in the literature. In this study, a new frame duplication detection method using Local Difference Binary (LDB) is proposed to extract features from the frames. Distance between similar frames that have similar feature vectors are is used by the method to estimate Distance of Forgery and to determine the exact location of duplicated frames. PSNR between similar frames are is then used to group them into three classes, and rule-based mechanism reports forged frames according to the membership to classes. Experimental results indicate that the proposed method has lower execution time with higher accuracy than similar works.

New local difference binary image descriptor and algorithm for rapid and precise vehicle visual localisation

Autonomous vehicle self‐localisation by scene matching under extreme environmental changes has been among the most challenging problems in robotics and computer vision in the last few years. Large dynamic illumination changes during the day and appearance changes between different seasons are the major difficulties about this problem, especially when the comparison is made between day‐time and night‐time images for the same scene. This study presents a new extended local difference binary (ELDB) image descriptor that represents a robust appearance invariant extension for the state‐of‐the‐art local difference binary (LDB) image descriptor. This study also introduces a new algorithm for vehicle visual localisation under extreme environmental changes. The new algorithm uses ELDB for image matching, and uses a modified multi‐hypothesis version of the Markov localisation (MHML) filter for self‐localisation. Experimental results show that the proposed modified MHML has reduced computational cost and has resulted in a faster cycle rate. Furthermore, these results show that ELDB has an improved image matching accuracy and requires less processing time compared to the original LDB. The proposed vision‐based vehicle localisation algorithm is shown to be faster and more accurate than other state‐of‐the‐art algorithms.

Moving object detection in aerial infrared images with registration accuracy prediction and feature points selection

Moving object detection in aerial infrared sequences is widely used in many applications, such as automatic traffic monitoring, border protection, and area surveillance. Feature-based image registration is the key step to compensate the background motion before detecting the moving objects. However, in practice it is often difficult to ensure the accurate registration, resulting in incomplete background compensation and thus decreasing detection performance. We find that the feature points in the object regions (FPOs) always impede the accurate registration of background. Besides, when the inlier points chosen by RANSAC excessively concentrate over the image, it will lead to inaccurate registration, especially in the case of insufficient feature points. These two issues are seldom studied before. In this paper, we propose a new framework of moving object detection, in which feature points selection and registration accuracy prediction are devised to improve detection accuracy. To do this, the detection information of previous frame is fed back to feature extraction of current frame for eliminating FPOs. Moreover, a quantitative metric is presented to measure the concentration of inlier points’ distribution over the image, with which one can predict the registration accuracy and determine whether to introduce additional cues for improving detection accuracy. Furthermore, we comprehensively investigate several classical feature extractors for aerial infrared image registration in terms of accuracy and running time, and suggest Speeded Up Robust Features (SURF) as feature detector and Local Difference Binary (LDB) as feature descriptor for image registration in aerial infrared sequences. Experimental results on benchmark infrared sequences show that our proposed method can greatly reduce false positives and also suppress false negatives, and performs favorably in terms of accuracy and efficiency.

Local difference ternary sequences descriptor based on unsupervised min redundancy mutual information feature selection

Texture feature description research have received significant attention in recent years. It is widely known that the local texture feature descriptor can achieve good performance under various image conditions, such as geometric size variation, different poses, complex illumination and partial occlusion. Although Local Difference Binary is an acknowledged excellent feature descriptor, it only computes the intensity and gradient difference on pairwise grid cells and ignores the image grid texture intensity and gradient. This paper proposes a novel local texture descriptor, named as Local Difference Ternary (LDT), which can not only represent difference and texture information of the grid cells intensity and gradient simultaneously, but also capture richer detailed texture information. In addition, the Unsupervised Min Redundancy Mutual Information (UMRMI) for feature selection is proposed to select the optimal subset of LDT features for achieving more powerfully discriminative ability. For the purpose of further improving the efficiency and effectiveness of UMRMI, we extend UMRMI to k-means space, namely k-UMRMI. Furthermore, a multi-degree scheme is adopted to achieve richer texture description. Finally, Radial Function Neural Network is employed for classification, which is an excellent classifier, especially for larger samples. Several experimental results on certain benchmark face databases demonstrate that our proposed method is remarkably superior to some other state-of-the-art approaches under various image conditions.

Learning Optimized Local Difference Binaries for Scalable Augmented Reality on Mobile Devices

The efficiency, robustness and distinctiveness of a feature descriptor are critical to the user experience and scalability of a mobile augmented reality (AR) system. However, existing descriptors are either too computationally expensive to achieve real-time performance on a mobile device such as a smartphone or tablet, or not sufficiently robust and distinctive to identify correct matches from a large database. As a result, current mobile AR systems still only have limited capabilities, which greatly restrict their deployment in practice. In this paper, we propose a highly efficient, robust and distinctive binary descriptor, called Learning-based Local Difference Binary (LLDB). LLDB directly computes a binary string for an image patch using simple intensity and gradient difference tests on pairwise grid cells within the patch. To select an optimized set of grid cell pairs, we densely sample grid cells from an image patch and then leverage a modified AdaBoost algorithm to automatically extract a small set of critical ones with the goal of maximizing the Hamming distance between mismatches while minimizing it between matches. Experimental results demonstrate that LLDB is extremely fast to compute and to match against a large database due to its high robustness and distinctiveness. Compared to the state-of-the-art binary descriptors, primarily designed for speed, LLDB has similar efficiency for descriptor construction, while achieving a greater accuracy and faster matching speed when matching over a large database with 2.3M descriptors on mobile devices.