Locally Adaptive Regression Kernel Research Articles

Pointer-type instrument positioning method of intelligent inspection system for substation

Robot intelligent inspection is widely used in the positioning of various pointer instruments in power, petroleum, chemical, and other industries. Aiming at the technical problems of poor adaptability, poor real-time performance, and low positioning accuracy of the pointer instrument positioning method in the existing substation intelligent inspection robot system, we propose a simple and effective pointer instrument positioning detection algorithm. The algorithm first extracts locally adaptive regression kernels (LARK) features of the input image, and the dimension of the LARK feature is reduced using the principal components analysis algorithm. Then, the template image is slid in the input image, the cosine similarity is used as an evaluation index, and the Fourier transform is used to accelerate the convolution operation in the cosine similarity calculation. Finally, the accelerated-KAZE algorithm is used to extract the feature points of the pointer-type instrument area image and the template image, and the statistical method of grid motion was used to eliminate the wrong matching points. The remaining matching points were processed by random sample consensus algorithm, and the homography matrix was obtained. The image registration was completed by the homography matrix, and the pointer-type instrument region positioning was realized. The experimental results show that the proposed method has good adaptability, strong real-time performance, and high accuracy of pointer-type instrument positioning.

Robust visual tracking based on response stability

In this paper, a new approach of response stability based for visual object tracking is developed. This approach proposes a response stability criterion to measure the tracking quality and fuse tracking results of multiple layers of a convolutional neural network (CNN). Inspired by recent detection based methods for visual tracking, the detection capability of EdgeBoxes is investigated, and proposes to re-detect target when tracking failure occurs. In addition, 3D locally adaptive regression kernels (LARK) feature is employed in correlation filter based tracking framework. Extensive experimental results and performance compared with state-of-the-art tracking algorithms on challenging benchmark datasets show that our method is more accurate and robust.

A robust visual tracking method via local feature extraction and saliency detection

Visual object tracking is a fundamental problem in computer vision. It heavily relies on feature description for the appearance of object. In this paper, we present a robust algorithm which exploits the locally adaptive regression kernel (LARK) feature for visual tracking. The proposed approach formulates the LARK feature in a tracking by detection framework. In addition, we compute a target-specific saliency map as LARK feature with the guidance of the tracking framework. The tracking problem is solved by maximizing an object location likelihood function. We adopt Fast Fourier Transform for fast learning and detection in this work. Extensive experimental results on challenging videos show that the proposed algorithm performs favorably against state-of-the-art methods in terms of accuracy and robustness.

Detection based visual tracking with convolutional neural network

In this paper, we propose a detection strategy based visual object tracking algorithm. We employ multiple trackers using layers of deep convolutional neural network (CNN) features. Each tracker which is correlation filter based tracking framework tracks an object forwardly and then backwardly. By analyzing the forward and backward trajectories, we measure the robustness of tracking results. A detection strategy which is based on locally adaptive regression kernels (LARK) feature is carried out according to the robustness of tracking result. Target can be located from the provided candidates. Extensive experimental results show that the proposed method improves the accuracy and robustness of tracking, achieving state-of-the-art results on several recent benchmark datasets.

Robust UAV-based Tracking Using Hybrid Classifiers.

Visual object tracking is a key factor for unmanned aerial vehicles (UAVs). In this paper, we propose a robust and effective visual object tracking method with an appearance model based on the locally adaptive regression kernel (LARK). The proposed appearance model encodes the geometric structure of the target. The tracking problem is formulated as two binary classifiers via two support vector machines (SVMs) with online model update. The backward tracking which tracks the target in reverse of time is utilized to evaluate the accuracy and robustness of the two SVMs. The final locations are adaptively fused based on the results of the forward tracking and backward tracking validation. Several state-of-the-art tracking algorithms are evaluated on large scale benchmark datasets which include challenging factors such as heavy occlusion, pose variation, illumination variation and motion blur. Experimental results demonstrate that our method achieves appealing performance.

Sparse Locally Adaptive Regression Kernel For Face Verification

The paper presents several thresholds obtained by heuristic approach for face verification using Locally Adaptive Regression Kernel (LARK) descriptors for euclidean, cosine and chebyshev distance metrics. The absence of a threshold for several distance metrics possess several setbacks such as increased computational complexity and escalated runtime. The proposed method has significantly higher influence when the verification process is computationally intensive. The proposed approach requires minimal training and face verification is accomplished based on the threshold value obtained during training. The whole process is modest and nearly all of the time spent is solely on quantifying any of the distance metrics between the LARKs obtained from the two faces for verification. LARK descriptors compute a measure of resemblance on the basis of “signal-induced distance” between a pixel and its nearby pixels. We assess the interspace between the LARKs from these faces and analogize the resemblance from the threshold resulting in a binary decision.

Infrared object detection using global and local cues based on LARK

Object detection has become a challenging problem in computer vision. Locally Adaptive Regression Kernel (LARK) based detection methods are able to produce visually pleasing results without any training. We in this paper present an effective object detection method by exploring global and local cues based on LARK features. First, we encode the local context similarity by exploiting region Structural LARK (SLARK) features, which measure the likeness of a pixel to its surroundings in the query image and the test image. Second, a global constraint based on SLARK features via Heat equation is learned to detect similar features in the test image. Results from matrix cosine similarity are computed to estimate similar regions between these computed features. A compactness score is provided to refine these regions. Next, we detect the location of objects in the test image using non-maxima suppression. We show in experiments that the proposed method significantly outperforms other methods on the infrared image datasets, localizing the objects in the test images effectively.

Automatic false edge elimination using locally adaptive regression kernel

The discrimination of true and false edges in edge images is a challenging yet important problem that has not attracted the mainstream research community in image processing. Existing approaches often emphasize on detecting true edges while neglecting the handling of false edges. In addition, many existing techniques are complicated in nature, non-robust for handling different type of images, and suitable only for specific applications. In this paper, we proposed a technique that eliminates false edges from a binary edge image. We employed locally adaptive regression kernel (LARK) as descriptor of the detected edge. By using LARK, we identified false edges by comparing their descriptors with those from the reference flat region. All edges with descriptors similar to the reference flat region were labeled as false edges and eliminated. We tested our algorithm on edge images obtained from the widely used Canny edge detector and conducted qualitative and quantitative analysis on the proposed method. Extensive simulation results show that the proposed method successfully eliminates most false edges. Comparison between the proposed method with some famous edge detectors shows that our algorithm quantitatively outperforms others with an average Baddeley’s delta metric of 23.37.

PLOW Filter for Color Image Denoising

In this paper, a denoising approach, which exploits patchredundancy for removing Gaussian noise from RGB color images is described. Both geometrical and photometrical similarity of image patches have to be considered for learning the parameters of this Patch-based Locally Optimal Weiner(PLOW) filer. K-means clustering,with LARK(Locally Adaptive Regression Kernel) features, is used to identify the geometrically similar patches. As opposed to traditional color image denoising approaches, that perform denoising in each color channel independently, this method performs denoising in the luminance-chrominance color space and thus exploits correlation across color components. Since the luminance component, Y, contains most valuable image features such as objects, shades, textures, edges and patterns etc., the information from the luminance component is only needed for clustering. Experimental results show that the denoising performance of the proposed method is better in terms of both peak signal-to-noise ratio and subjective visual quality.

Face Verification Using the LARK Representation

We present a novel face representation based on locally adaptive regression kernel (LARK) descriptors. Our LARK descriptor measures a self-similarity based on “signal-induced distance” between a center pixel and surrounding pixels in a local neighborhood. By applying principal component analysis (PCA) and a logistic function to LARK consecutively, we develop a new binary-like face representation which achieves state-of-the-art face verification performance on the challenging benchmark “Labeled Faces in the Wild” (LFW) dataset. In the case where training data are available, we employ one-shot similarity (OSS) based on linear discriminant analysis (LDA). The proposed approach achieves state-of-the-art performance on both the unsupervised setting and the image restrictive training setting (72.23% and 78.90% verification rates), respectively, as a single descriptor representation, with no preprocessing step. As opposed to combined 30 distances which achieve 85.13%, we achieve comparable performance (85.1%) with only 14 distances while significantly reducing computational complexity.