Real-time Video Object Detection Research Articles

A real-time object detection algorithm for video

Deep learning technology has been widely used in object detection. Although the deep learning technology greatly improves the accuracy of object detection, we also have the challenge of a high computational time. You Only Look Once (YOLO) is a network for object detection in images. In this paper, we propose a real-time object detection algorithm for videos based on the YOLO network. We eliminate the influence of the image background by image preprocessing, and then we train the Fast YOLO model for object detection to obtain the object information. Based on the Google Inception Net (GoogLeNet) architecture, we improve the YOLO network by using a small convolution operation to replace the original convolution operation, which can reduce the number of parameters and greatly shorten the time for object detection. Our Fast YOLO algorithm can be applied to real-time object detection in video.

Real-time video object detection and classification using hybrid texture feature extraction

ABSTRACT In video processing, feature extraction and classification are necessary steps to classify the video frames. To improve accuracy, an efficient texture-based feature extraction is required. Also, before improving the feature extraction, the background subtraction step is almost equal to the ground truth level. An efficient real-time video object recognition and classification utilizing hybrid texture feature extraction are proposed. A stationary wavelet transform-based joint bilateral filtering is used to remove the noise. An effective background subtraction is employed before extracting the features. In feature extraction, hybrid texture feature extraction is proposed where gray level co-occurrence matrix (GLCM) and discrete wavelet transform (DWT) features are combined and applied to the categorization process. The GLCM is used to extract the second-order statistical texture features for the estimation of motion in the videos. And, the DWT algorithm reduces the storage space in real-time video processing. The main objectives are to implement the real-time video object detection and classification using the hybrid texture feature extraction method called the GLCM-DWT technique, and investigate the performance evaluation of the proposed methodology and compare with the existing technique. The parameters, namely accuracy, sensitivity, specificity, and execution time are to be evaluated for the proposed algorithm in the MATLAB software.

Fast Deep Neural Networks With Knowledge Guided Training and Predicted Regions of Interests for Real-Time Video Object Detection

It has been recognized that deeper and wider neural networks are continuously advancing the state-of-the-art performance of various computer vision and machine learning tasks. However, they often require large sets of labeled data for effective training and suffer from extremely high computational complexity, preventing them from being deployed in real-time systems, for example vehicle object detection from vehicle cameras for assisted driving. In this paper, we aim to develop a fast deep neural network for real-time video object detection by exploring the ideas of knowledge-guided training and predicted regions of interest. Specifically, we will develop a new framework for training deep neural networks on datasets with limited labeled samples using cross-network knowledge projection which is able to improve the network performance while reducing the overall computational complexity significantly. A large pre-trained teacher network is used to observe samples from the training data. A projection matrix is learned to project this teacher-level knowledge and its visual representations from an intermediate layer of the teacher network to an intermediate layer of a thinner and faster student network to guide and regulate the training process. To further speed up the network, we propose to train a low-complexity object detection using traditional machine learning methods, such as support vector machine. Using this low-complexity object detector, we identify the regions of interest that contain the target objects with high confidence. We obtain a mathematical formula to estimate the regions of interest to save the computation for each convolution layer. Our experimental results on vehicle detection from videos demonstrated that the proposed method is able to speed up the network by up to 16 times while maintaining the object detection performance.

Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video

Object detection is considered one of the most challenging problemsin this field of computer vision, as it involves the combinationof object classification and object localization within a scene. Recently,deep neural networks (DNNs) have been demonstrated toachieve superior object detection performance compared to otherapproaches, with YOLOv2 (an improved You Only Look Once model)being one of the state-of-the-art in DNN-based object detectionmethods in terms of both speed and accuracy. Although YOLOv2can achieve real-time performance on a powerful GPU, it still remainsvery challenging for leveraging this approach for real-timeobject detection in video on embedded computing devices withlimited computational power and limited memory. In this paper,we propose a new framework called Fast YOLO, a fast You OnlyLook Once framework which accelerates YOLOv2 to be able toperform object detection in video on embedded devices in a realtimemanner. First, we leverage the evolutionary deep intelligenceframework to evolve the YOLOv2 network architecture and producean optimized architecture (referred to as O-YOLOv2 here) that has2.8X fewer parameters with just a 2% IOU drop. To further reducepower consumption on embedded devices while maintaining performance,a motion-adaptive inference method is introduced intothe proposed Fast YOLO framework to reduce the frequency ofdeep inference with O-YOLOv2 based on temporal motion characteristics.Experimental results show that the proposed Fast YOLOframework can reduce the number of deep inferences by an averageof 38.13%, and an average speedup of 3.3X for objectiondetection in video compared to the original YOLOv2, leading FastYOLO to run an average of 18FPS on a Nvidia Jetson TX1 embeddedsystem.

Real-time running event detection via a community patrol robot

Security surveillance is an important application for patrol robots. In this article, a real-time running event detection method is proposed for the community patrol robot. Although sliding window-based approaches have been quite successful in detecting objects in images, directly extending them to real-time object detection in video is not simple. This is due to the huge samples and diversity of object appearances with multivisual view and scale. To address these limitations, first, a simple and effective spatial–temporal filtering-based approach is proposed to obtain moving object proposals in each frame; then, two-stream convolutional networks fusion architecture is introduced to best take advantage of the spatial–temporal information from the proposal. The algorithm is applied on PatrolBot in community environments and runs at 15 fps on a consumer laptop. Two benchmark data sets (the Kungliga Tekniska Högskolan [KTH] data set and Nanyang Technological University [NTU] running data set) were also used to compare results with previous works. Experimental results show higher accuracy and lower detection error rate in the proposed method.

Video Foreground Detection Based on Symmetric Alpha-Stable Mixture Models

Background subtraction (BS) is an efficient technique for detecting moving objects in video sequences. A simple BS process involves building a model of the background and extracting regions of the foreground (moving objects) with the assumptions that the camera remains stationary and there exist no movements in the background. These assumptions restrict the applicability of BS methods to real-time object detection in video. In this letter, we propose an extended cluster BS technique with a mixture of symmetric alpha-stable (SαS) distributions. An online self-adaptive mechanism is presented that allows automated estimation of the model parameters using the log moment method. Results over real video sequences from indoor and outdoor environments, with data from static and moving video cameras are presented. The SαS mixture model is shown to improve the detection performance compared with a cluster BS method using a Gaussian mixture model and the method of Li et al.

Fast perceptual region tracking with coding-depth sensitive access for stream transcoding

Object-based bit allocation can result in significant improvement in the perceptual quality of extremely compressed video. However, real-time video object detection in large format high fidelity video is computationally daunting. Most algorithms begin with extensive use of classical bit analysis, and thus remain computationally heavy. Based on some recent results in human visual perception, in this paper, we present an experimental visual region tracking algorithm particularly designed for perceptual stream transcoding. This exploits the cue order observed in human visual perception to achieve very high computation speed as well as tracking efficiency. Rather than begin processing from pixel level or using any pixel level processing at all, it employs high level motion cue and block shape cue analysis to identify signatures of various relative movements between object of interest, scene background and the camera on the motion vector set, and from there it identifies objects. It then uses predictive filters to track the regions. The result is a fast yet highly effective perceptual region tracking algorithm that can operate in stream rate and track regions of perceptually significant object despite camera movements such as zoom, panning and translation. The technique is not specific to any special class of objects. We have implemented this algorithm in a live ISO-13818/MPEG-2 perceptual transcoder. In this paper, we share the performance of this implementation. This fast object-aware video rate transcoder is particularly suitable for live streaming and can convert a regular stream into a perceptually coded video stream.