• Cloud-based scalable object detection and classification in video streams

      Yaseen, Muhammad Usman; Anjum, Ashiq; Rana, Omer; Hill, Richard; University of Derby; Cardiff University (Elsevier, 2017-02-07)
      Due to the recent advances in cameras, cell phones and camcorders, particularly the resolution at which they can record an image/video, large amounts of data are generated daily. This video data is often so large that manually inspecting it for useful content can be time consuming and error prone, thereby it requires automated analysis to extract useful information and metadata. Existing video analysis systems lack automation, scalability and operate under a supervised learning domain, requiring substantial amounts of labelled data and training time. We present a cloud-based, automated video analysis system to process large numbers of video streams, where the underlying infrastructure is able to scale based on the number and size of the stream(s) being considered. The system automates the video analysis process and reduces manual intervention. An operator using this system only specifies which object of interest is to be located from the video streams. Video streams are then automatically fetched from the cloud storage and analysed in an unsupervised way. The proposed system was able to locate and classify an object of interest from one month of recorded video streams comprising 175 GB in size on a 15 node cloud in 6.52 h. The GPU powered infrastructure took 3 h to accomplish the same task. Occupancy of GPU resources in cloud is optimized and data transfer between CPU and GPU is minimized to achieve high performance. The scalability of the system is demonstrated along with a classification accuracy of 95%.
    • Cloud-based video analytics using convolutional neural networks.

      Yaseen, Muhammad Usman; Anjum, Ashiq; Farid, Mohsen; Antonopoulos, Nick; University of Derby; Department of Electronics, Computing and Mathematics; University of Derby; Derby UK; Department of Electronics, Computing and Mathematics; University of Derby; Derby UK; Department of Electronics, Computing and Mathematics; University of Derby; Derby UK; Department of Electronics, Computing and Mathematics; University of Derby; Derby UK (2018-09-13)
      Object classification is a vital part of any video analytics system, which could aid in complex applications such as object monitoring and management. Traditional video analytics systems work on shallow networks and are unable to harness the power of distributed processing for training and inference. We propose a cloud‐based video analytics system based on an optimally tuned convolutional neural network to classify objects from video streams. The tuning of convolutional neural network is empowered by in‐memory distributed computing. The object classification is performed by comparing the target object with the prestored trained patterns, generating a set of matching scores. The matching scores greater than an empirically determined threshold reveal the classification of the target object. The proposed system proved to be robust to classification errors with an accuracy and precision of 97% and 96%, respectively, and can be used as a general‐purpose video analytics system.
    • Deep learning hyper-parameter optimization for video analytics in clouds.

      Yaseen, Muhammad Usman; Anjum, Ashiq; Rana, Omer; Antonopoulos, Nikolaos; University of Derby; Cardiff University (IEEE, 2018-06-15)
      A system to perform video analytics is proposed using a dynamically tuned convolutional network. Videos are fetched from cloud storage, preprocessed, and a model for supporting classification is developed on these video streams using cloud-based infrastructure. A key focus in this paper is on tuning hyper-parameters associated with the deep learning algorithm used to construct the model. We further propose an automatic video object classification pipeline to validate the system. The mathematical model used to support hyper-parameter tuning improves performance of the proposed pipeline, and outcomes of various parameters on system's performance is compared. Subsequently, the parameters that contribute toward the most optimal performance are selected for the video object classification pipeline. Our experiment-based validation reveals an accuracy and precision of 97% and 96%, respectively. The system proved to be scalable, robust, and customizable for a variety of different applications.
    • High performance video processing in cloud data centres

      Yaseen, Muhammad Usman; Zafar, Muhammad Sarim; Anjum, Ashiq; Hill, Richard; University of Derby (IEEE, 2016-03)
      Mobile phones and affordable cameras are generating large amounts of video data. This data holds information regarding several activities and incidents. Video analytics systems have been introduced to extract valuable information from this data. However, most of these systems are expensive, require human supervision and are time consuming. The probability of extracting inaccurate information is also high due to human involvement. We have addressed these challenges by proposing a cloud based high performance video analytics platform. This platform attempts to minimize human intervention, reduce computation time and enables the processing of a large number of video streams. It achieves high performance by optimizing the occupancy of GPU resources in cloud and minimizing the data transfer by concurrently processing a large number of video streams. The proposed video processing platform is evaluated in three stages. The first evaluation was performed at the cloud level in order to evaluate the scalability of the platform. This evaluation includes fetching and distributing video streams and efficiently utilizing available resources within the cloud. The second valuation was performed at the individual cloud nodes. This evaluation includes measuring the occupancy level, effect of data transfer and the extent of concurrency achieved at each node. The third evaluation was performed at the frame level in order to determine the performance of object recognition algorithms. To measure this, compute intensive tasks of the Local Binary Pattern (LBP) algorithm have been ported on to the GPU resources. The platform proved to be very scalable with high throughput and performance when tested on a large number of video streams with increasing number of nodes.
    • Modeling and analysis of a deep learning pipeline for cloud based video analytics.

      Yaseen, Muhammad Usman; Anjum, Ashiq; Antonopoulos, Nikolaos; University of Derby; University of Derby, Derby, United Kingdom; University of Derby, Derby, United Kingdom; University of Derby, Derby, United Kingdom (2017-12-05)
      Video analytics systems based on deep learning approaches are becoming the basis of many widespread applications including smart cities to aid people and traffic monitoring. These systems necessitate massive amounts of labeled data and training time to perform fine tuning of hyper-parameters for object classification. We propose a cloud based video analytics system built upon an optimally tuned deep learning model to classify objects from video streams. The tuning of the hyper-parameters including learning rate, momentum, activation function and optimization algorithm is optimized through a mathematical model for efficient analysis of video streams. The system is capable of enhancing its own training data by performing transformations including rotation, flip and skew on the input dataset making it more robust and self-adaptive. The use of in-memory distributed training mechanism rapidly incorporates large number of distinguishing features from the training dataset - enabling the system to perform object classification with least human assistance and external support. The validation of the system is performed by means of an object classification case-study using a dataset of 100GB in size comprising of 88,432 video frames on an 8 node cloud. The extensive experimentation reveals an accuracy and precision of 0.97 and 0.96 respectively after a training of 6.8 hours. The system is scalable, robust to classification errors and can be customized for any real-life situation.
    • Spatial frequency based video stream analysis for object classification and recognition in clouds

      Yaseen, Muhammad Usman; Anjum, Ashiq; Antonopoulos, Nikolaos; University of Derby (IEEE, 2016-12-07)
      The recent rise in multimedia technology has made it easier to perform a number of tasks. One of these tasks is monitoring where cheap cameras are producing large amount of video data. This video data is then processed for object classification to extract useful information. However, the video data obtained by these cheap cameras is often of low quality and results in blur video content. Moreover, various illumination effects caused by lightning conditions also degrade the video quality. These effects present severe challenges for object classification. We present a cloud-based blur and illumination invariant approach for object classification from images and video data. The bi-dimensional empirical mode decomposition (BEMD) has been adopted to decompose a video frame into intrinsic mode functions (IMFs). These IMFs further undergo to first order Reisz transform to generate monogenic video frames. The analysis of each IMF has been carried out by observing its local properties (amplitude, phase and orientation) generated from each monogenic video frame. We propose a stack based hierarchy of local pattern features generated from the amplitudes of each IMF which results in blur and illumination invariant object classification. The extensive experimentation on video streams as well as publically available image datasets reveals that our system achieves high accuracy from 0.97 to 0.91 for increasing Gaussian blur ranging from 0.5 to 5 and outperforms state of the art techniques under uncontrolled conditions. The system also proved to be scalable with high throughput when tested on a number of video streams using cloud infrastructure.