Towards Intelligent Human Behavior Detection for Video Surveillance

Computer vision techniques are capable of detecting human behavior from video sequences. Several state-of-the-art techniques have been proposed for human behavior detection and analysis. However, a collective framework is always required for intelligent human behavior analysis. Therefore, in this chapter, the authors provide a comprehensive understanding towards human behavior detection approaches. The framework of this chapter is based on human detection, human tracking, and human activity recognition, as these are the basic steps of human behavior detection process. The authors provide a detailed discussion over the human behavior detection framework and discuss the feature-descriptor-based approach. Furthermore, they have provided qualitative and quantitative analysis for the detection framework and demonstrate the results for human detection, human tracking, and human activity recognition.

Object Recognition Pipeline

Object grasping in domestic environments using social robots has an enormous potential to help dependent people with a certain degree of disability. In this chapter, the authors make use of the well-known Pepper social robot to carry out such task. They provide an integrated solution using ROS to recognize and grasp simple objects. That system was deployed on an accelerator platform (Jetson TX1) to be able to perform object recognition in real time using RGB-D sensors attached to the robot. By using the system, the authors prove that the Pepper robot shows a great potential for such domestic assistance tasks.

Applying Cellular Automata-Based Structures to Hyperspectral Image Processing

This chapter addresses the problem of processing hyperspectral images (HI) and sequences leading to high efficiency implementations. A new methodology based on the application of cellular automata (CA) is presented to solve two different processing tasks, the segmentation and denoising of HI and sequences, respectively. CA structures present potential benefits over traditional approaches since they are computationally efficient and can adapt to the particularities of the task to be solved. However, it is necessary to generate an appropriate rule set for each particular problem, which is usually a difficult task. The generation of the rule sets is handled here following a new methodology based on the application of evolutionary algorithms and using synthetic low-dimensionality images and sequences as training datasets, which results in CA structures that can be used to process HI and sequences successfully, thus avoiding the problem of lack of labeled reference images. Both processing approaches have been tested over real HI providing very competitive results.

A Secured Contactless Fingerprint Verification Method Using a Minutiae Matching Technique

Most matching or verification phases of fingerprint systems use minutiae types and orientation angle to find matched minutiae pairs from the input and template fingerprints. Unfortunately, due to some non-linear distortions, like excessive pressure and fingers twisting during enrollment, this process can cause the minutiae features to be distorted from the original. The authors are interested in a fingerprint matching method using contactless images for fingerprint verification. After features extraction, they compute Euclidean distances between template minutiae (bifurcation and ending points) and input image minutiae. They compute then after bifurcation ridges orientation angles and ending point orientations. In the decision stage, they analyze the similarity between templates. The proposed algorithm has been tested on a set of 420 fingerprint images. The verification accuracy is found to be acceptable and the experimental results are promising. Future work will enhance the proposed verification method by a new template protection technique.

Role of Clustering Techniques in Effective Image Segmentation

Image segmentation is gauged as an essential stage of representation in image processing. This process segregates a digitized image into various categorized sections. An additional advantage of distinguishing dissimilar objects can be represented within this state of the art. Numerous image segmentation techniques have been proposed by various researchers, which maintained a smooth and easy timely evaluation. In this chapter, an introduction to image processing along with segmentation techniques, computer vision fundamentals, and its applied applications that will be of worth to the image processing and computer vision research communities has been deeply studied. It aims to interpret the role of various clustering-based image segmentation techniques specifically. Use of the proposed chapter if made in real time can project better outcomes in object detection and recognition, which can then later be applied in numerous applications and devices like in robots, automation, medical equipment, etc. for safety, advancement, and betterment of society.

Robust 3D Visual Localization Based on RTABmaps

Visual localization is a key capability in robotics and in augmented reality applications. It estimates the 3D position of a camera on real time just analyzing the image stream. This chapter presents a robust map-based 3D visual localization system. It relies on maps of the scenarios built with the known tool RTABmap. It consists of three steps on continuous loop: feature points computation on the input frame, matching with feature points on the map keyframes (using kNN and outlier rejection), and 3D final estimation using PnP geometry and optimization. The system has been experimentally validated in several scenarios. In addition, an empirical study of the effect of three matching outlier rejection mechanisms (radio test, fundamental matrix, and homography matrix) on the quality of estimated 3D localization has been performed. The outlier rejection mechanisms, combined themselves or alone, reduce the number of matched feature points but increase their quality, and so, the accuracy of the 3D estimation. The combination of ratio test and homography matrix provides the best results.

Novel Techniques in Skin and Face Detection in Color Images

Human skin detection and face detection are important and challenging problems in computer vision. The use of color information has increased in recent years due to the lower processing time of face detection compared to black and white images. A number of techniques for skin detection are discussed. Experiments have been performed utilizing deep learning with a variety of color spaces, showing that deep learning produces better results compared to methods such as rule-based, Gaussian model, and feed forward neural network on skin detection. A challenging problem in skin detection is that there are numerous objects with colors similar to that of the human skin. A texture segmentation method has been designed to distinguish between the human skin and objects with similar colors to that of human skin. Once the skin is detected, image is divided into several skin components and the process of detecting the face is limited to these components—increasing the speed of the face detection. In addition, a method for eye and lip detection is proposed using information from different color spaces.

Bag of Visual Words Based on Co-HOG Features for Word Spotting in Handwritten Documents

In this chapter, the authors present a segmentation-based word spotting method for handwritten documents using bag of visual words (BoVW) framework based on co-occurrence histograms of oriented gradients (Co-HOG) features. The Co-HOG descriptor captures the word image shape information and encodes the local spatial information by counting the co-occurrence of gradient orientation of neighbor pixel pairs. The handwritten document images are segmented into words and each word image is represented by a vector that contains the frequency of visual words appeared in the image. In order to include spatial information to the BoVW framework, the authors adopted spatial pyramid matching (SPM) method. The proposed method is evaluated using precision and recall metrics through experimentation conducted on popular datasets such as GW and IAM. The performance analysis confirmed that the method outperforms existing word spotting techniques.

A Survey of 3D Rigid Registration Methods for RGB-D Cameras

Registration of multiple 3D data sets is a fundamental problem in many areas. Many researches and applications are using low-cost RGB-D sensors for 3D data acquisition. In general terms, the registration problem tries to find a transformation between two coordinate systems that better aligns the point sets. In order to review and describe the state-of-the-art of the rigid registration approaches, the authors decided to classify methods in coarse and fine. Due to the high variety of methods, they have made a study of the registration techniques, which could use RGB-D sensors in static scenarios. This chapter covers most of the expected aspects to consider when a registration technique has to be used with RGB-D sensors. Moreover, in order to establish a taxonomy of the different methods, the authors have classified those using different characteristics. As a result, they present a classification that aims to be a guide to help the researchers or practitioners to select a method based on the requirements of a specific registration problem.