Object detection with Gabor filters and cumulative histograms

Distance Based k-NN Classification of Gabor Jet Local Descriptors

Object region proposal has a wide application on various domains, such as object detection, object tracking, robot navigation, and anomaly detection. Widely used region proposal methods are based on either grouping superpixels or sliding windows. Previous studies have been done by grouping either convolution features, superpixels, or windows. Moreover, histogram of gradients (HoGs) of lower-level features (pixels) can be used for the region proposal task. In this study, both the concepts of HoGs and convolution features are used for proposing object(s) region(s) in an image. Region proposal is done by HoGs of convolution features and statistical application on the gradient data of different feature maps. First, a sized image is passed through one convolution layer to generate reduced feature maps. Then, a window slides over each feature map and HoG is applied over each window. Thereafter, the histogram is analysed using the concept of Coefficient of Variation (CV) and angle (slope) applied on histogram data values. A window is considered as the object region if the CV and angle of its histogram data exceed some thresholds. For all feature maps, we have obtained several widows that represent approximated object regions. These windows are grouped to obtain the possible region(s) proposal. The effectiveness of the proposed method is demonstrated over one of the benchmark datasets, called `PASCAL VOC'. Our method is found superior to two other state-of-the-art, namely region-based segmentation (RBS), and combining efficient object localization and image classification (CEOLIC) in terms of recall.

2-D Gabor filter based transition region extraction and morphological operation for image segmentation

The convolutional neural networks (CNNs) have recently demonstrated to be a powerful tool for object detection. However, with the complex scenes in remote sensing images, feature extraction of the object in the CNN will be seriously affected by background information. To address this issue, in this article, a region-enhanced CNN (RECNN) is proposed for the object detection of remote sensing images. The RECNN introduces the saliency constraint and multilayer fusion strategy into the CNN model, which can effectively enhance the object regions for better detection. Specifically, the saliency map is extracted and utilized to guide the training of the proposed model to strengthen saliency regions in feature maps. In addition, since different layers can reflect the object regions in varied resolutions, a multilayer fusion strategy is introduced to connect different convolutional layers and explore the context, where the feature maps of object regions are further enhanced. Experimental results on a publicly available ten-class object detection data set demonstrate the superiority of the RECNN over several competitive object detection methods.

A vision-based driver assistance system using image processing technology consists of three main modules: road detection, traffic sign detection/identification, obstacle detection. Traffic Sign Recognition is an upcoming research field under applied Computer Vision and Machine Learning which deals with the automatic detection and classification of traffic signs in traffic scene images. In the current paper, we discuss the methodology used to detect the road sign from a traffic sign scene image and present a technique that can be used to construct a system that recognizes road signs in images. Such a system will ensure that each driver is aware of the rules & hazards on the road & will thus help in improving road safety. Also, the location of the road sign in the traffic sign image is unknown. Once these obstacles are overcome, such a system could be integrated in a Driver Assistance System. The primary objective is to develop an algorithm, which will identify various types of road signs from streaming video of real time road scenes in a reasonable time frame. The algorithm has two main parts: the first one, detection which uses the color and shape information to detect a road sign in a traffic scene picture. The second one, prediction & classification based on Neural Network concept. Our algorithm proposes a variety of MATLAB Image Processing Toolbox commands to determine if a road sign is present in current image. If present, the sign is resized and certain features from the Region of Interest (RoI) are fed as a feature vector to a neural net. This trained Neural Classifier then predicts the class of the road sign. Genetic Algorithms (GA) with built-in intelligence could be incorporated into the current system which will try to look for traffic signs only in environments where there is probability of finding/detecting one.

In this paper, we propose the identification method of artifacts in scenery images using color and line information. In the proposed method, the original image is divided into some areas based on color information, and whether or not artifacts are included for each divided area are judged using color and line information. The proposed method judges for each area in three level; (1) there is no artifacts, (2) there may be artifacts, and (3) it has a high possibility containing artifacts. We carried out a series of computer experiments and confirmed that the proposed method can identify the area including artifacts in 91.3%.

This paper presents a method for extracting regions of non-rigid moving objects from a video. The proposed method utilizes interactive image cutout and local affine transformation. In the proposed method, once a user draws seed-lines on the object and background regions of the first frame of a video, the seed-lines are automatically tracked to next frames based on local affine transformation, and the object regions in each frame are automatically extracted by image cutout using the tracked seed-lines. Experimental results have shown that the proposed method can correctly extract the regions of nonrigid objects from a video.

As a unique biometric trait, the research of sclera blood vessels have becomes active recently, because the sclera vessels can be captured under visible-wavelength light condition rather than near infrared light condition. However, the performance of sclera identification system degrades a lot due to unsatisfactory sclera segmentation and tedious extraction process. In this paper, we propose a novel sclera segmentation algorithm and an improved sclera vessels extraction method. The accurate and efficient sclera segmentation method is proposed based on improved OSTU algorithm. Besides, the vessels extraction method is put forward by adaptive histogram equalization method and Gabor filters. The experimental results on UBIRIS.vl database prove that the proposed sclera vessels extraction algorithm performs well and the sclera segmentation method has an obvious improvement in terms of efficiency and accuracy over than other segmentation algorithms.

In this paper, we present an adaptive background generation method for automatic selection of initial object region for simultaneous object detection and depth estimation using the MCA camera. We then estimate color shifting vectors (CSVs) of the extracted object's region using simplified elastic registration algorithm in the pyramid-based multi-resolution framework. Using the color shifting property of the MCA camera, the depth of the object's region is estimated from CSVs. The proposed method uses only one camera for object detection and depth estimation. Experimental results show that the MCA camera-based object tracking system can be used in various consumer surveillance systems.

Object detection and tracking has always been one of the important research directions in computer vision. The purpose is to determine whether the object is contained in the input image and enclose the object with a bounding box. However, most object detection and tracking methods are applied to daytime objects, and the processing of nighttime objects is imprecise. In this paper, a spectral-spatial feature enhancement algorithm for nighttime object detection and tracking is proposed, which is inspired by symmetrical neural networks. The proposed method consists of the following steps. First, preprocessing is performed on unlabeled nighttime images, including low-light enhancement, object detection, and dynamic programming. Second, object features for daytime and nighttime times are extracted and modulated with a domain-adaptive structure. Third, the Siamese network can make full use of daytime and nighttime object features, which is trained as a tracker by the above images. Fourth, the test set is subjected to feature enhancement and then input to the tracker to obtain the final detection and tracking results. The feature enhancement step includes low-light enhancement and Gabor filtering. The spatial-spectral features of the target are fully extracted in this step. The NAT2021 dataset is used in the experiments. Six methods are employed as comparisons. Multiple judgment indicators were used to analyze the research results. The experimental results show that the method achieves excellent detection and tracking performance.

Gabor filter is a widely used feature extraction method, especially in image texture analysis. The selection of optimal filter parameters is usually problematic and unclear. This study analyzes the filter design essentials and proposes two different methods to segment the Gabor filtered multi-channel images. The first method integrates Gabor filters with labeling algorithm for edge detection and object segmentation. The second method uses the K-means clustering with simulated annealing for image segmentation of a stack of Gabor filtered multi-channel images. Various experiments with real images demonstrate the effectiveness of these approaches.

Sonar image object detection is essential in underwater rescue and resource exploration. Although many convolution neural network (CNN)-based object detection algorithms have achieved great success in natural images. However, for underwater sonar images, problems, such as seabed reverberation noise interference, low proportion of foreground object region pixels, and poor imaging resolution, present considerable challenges to achieving accurate underwater object detection. To address these problems, we propose a novel sonar image object detector called the multilevel feature fusion network (MLFFNet). The detector consists of multiscale convolution module (MS-Conv), multilevel feature extraction module (ML-FEM), multilevel feature fusion module (ML-FFM), neighborhood channel attention mechanism (N-CAM), multiscale feature pyramid module (MS-FPN), and feature association module (FA). First, we use the MS-Conv to extract different scale feature information in the object region. Second, the ML-FEM and ML-FFM are used to obtain the local detail and global context features. Third, the N-CAM and MS-FPN are used to obtain the foreground objects’ semantic feature and position feature, and suppress the background region noise interference. Finally, we use the FA module to enhance the category and feature correlation of different objects. Extensive experiments are conducted on the real scene sonar image dataset. The experimental results demonstrate that MLFFNet performs better than other state-of-the-art object detection methods. Code and dataset are publicly at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/darkseid-arch/SonarMLFFNet</uri> .

In transfer learning, for a given classification task, the learning from source domain into target domain is achieved by training/transferring a pre-trained network with data from target domain. During this process, a pre-trained network is a pre-requisite for transferring the knowledge from source domain into the target domain. In this study, to eliminate the need for such a pre-trained model, Gabor filters are utilized. In the proposed method, a Convolutional Neural Network is constructed by initializing its first convolutional layer, which represents the low-level features, such as corners and edges, with Gabor filters that have similar low-level characteristics. Experimental results on MNIST, CIFAR-10, and CIFAR-100 datasets show that Gabor filters based initialization of the network has similar characteristics with model transfer and can be applied for transfer learning without using a pre-trained model.

This paper proposes a new algorithm for detecting vehicles from an image. An image is at the first segmented into regions by using not only color information but also Gabor transformation of grayscale image. Second, candidate regions corresponding to a vehicle are extracted using affine moment invariants. Third, a true region for a vehicle is selected from candidate regions using normalized cumulative histogram of grayscale in a window which is set for a candidate region of interest, and from the selected region the area of a vehicle is detected.

Recently, fast and accurate DNN object detectors such as YOLO and SSD have attracted considerable attention. However, it still takes far more time than real time processing when inputting a 4K video and becomes even more challenging when inputting multi-view 4K sports videos due to the massive amount of data and small objects. This paper presents a novel approach to significantly accelerate object detection. Observing the fact that object regions (including players and balls) are very sparse in sports videos, we crop the images to greatly reduce the processing areas using the temporal or view correlations. However, simple image cropping may worsen the accuracy if the object is too small to be detected. A further observation is that the detection can be improved by resizing the small objects properly. Our experimental results on two soccer matches of J1 League demonstrate that we can make the detection much faster with a high accuracy for small objects.