Kahlil Muchtar

Real-time background modeling based on a multi-level texture description

Background construction is the base of object detection and tracking of machine vision systems. Traditional background modeling methods often require complicated computations and are sensitive to illumination changes. This paper proposes a novel block-based background modeling method based on a hierarchical coarse-to-fine texture description, which fully utilizes the texture characteristics of each incoming frame. The proposed method is efficient and can resist both illumination changes and shadow disturbance. The experimental results show that this method is suitable for real-world scenes and real-time applications.

Three-Pronged Compensation and Hysteresis Thresholding for Moving Object Detection in Real-Time Video Surveillance

Moving object extraction is the core of event detection in video surveillance. Although many related methods have been proposed to extract moving objects, even advanced applications still encounter cavity problems, which are false detection and deficiencies resulting from cavities inside the body or fragmented foreground objects. In this paper, an entirely new structure for extracting moving objects is proposed. This scheme is based on the concepts of hysteresis thresholding and motion compensation, which constitute spatial and temporal compensations, respectively. Experimental results show that the proposed scheme can outperform modern moving object detection methods in terms of precision, recall, F-measure, and other measurements.

Privacy-preserving multimedia cloud computing via compressive sensing and sparse representation

Cloud computing is an emerging technology developed for providing various computing and storage services over the Internet. In this paper, we proposed a privacy-preserving cloud-aware scenario for compressive multimedia applications, including multimedia compression, adaptation, editing/manipulation, enhancement, retrieval, and recognition. In the proposed framework, we investigate the applicability of our/existing compressive sensing (CS)-based multimedia compression and securely compressive multimedia “trans-sensing” techniques based on sparse coding for securely delivering compressively sensed multimedia data over a cloud-aware scenario. Moreover, we also investigate the applicability of our/existing sparse coding-based frameworks for several multimedia applications by leveraging the strong capability of a media cloud. More specifically, to consider several fundamental challenges for multimedia cloud computing, such as security and network/device heterogeneities, we investigate the applications of CS and sparse coding techniques in multimedia delivery and applications. As a result, we can build a unified cloud-aware framework for privacy-preserving multimedia applications via sparse coding.

Abandoned object detection in complicated environments

In video surveillance, tracking-based approaches are very popular especially for detecting abandoned objects in public areas. Once the object has been tracked, the object status can be further classified as removed or abandoned. However, some shortcomings were found on tracking-based approaches, e.g. illumination changes and occlusion. Therefore, in this paper, an alternative approach to detect abandoned objects is proposed by incorporating background modeling and Markov model. In addition the shadow removal is employed to rectify detected objects and obtain more accurate results. The experimental results show that the proposed scheme is better than other methods in terms of accuracy and correctness.

Moving object detection in the encrypted domain

The privacy-preserving moving object detection has drawn a lot of interest lately. Nevertheless, current approaches use Paillier’s scheme for encryption that impractical in real-time applications due to high computational complexity. In addition, none of them are fully compatible with popular background modeling methods. In this paper, a fast and secure encryption scheme for a surveillance system has been proposed. The algorithm allows the detection of a moving object to be implemented directly in the encryption domain. The proposed scheme separates every pixel into two parts. The first part of a pixel (most significant bits) is scrambled to encrypt the image, and the second part of the pixel (least significant bits) remains unchanged. This strategy allows the proposed encryption scheme to be compatible with the mixture of Gaussians (GMM) that is one of the most widely used background modeling methods to detect moving objects. The proposed scheme requires low computations and produces almost the same detection result as the GMM when it is applied to unencrypted videos. Security analysis of the proposed method also proves the robustness of the encryption process.

Secure multicasting of images via joint privacy-preserving fingerprinting, decryption, and authentication

Introduce a joint privacy-preserving fingerprinting, decryption, and authentication.Prevent encrypted data from being tampered without additional hash code/digest.Achieve the lightweight encryption/decryption, and low transmission cost. Joint fingerprinting and decryption (JFD) is useful in securing media transmission and distribution in a multicasting environment. Common drawbacks of the existing JFD methods are the transmitted data may leak the content of data, and a subscriber cannot determine if a received image is modified such that tampering attack can be mounted successfully. Here we focus on security and privacy of image multicasting and introduce a new framework called JFDA (joint privacy-preserving fingerprinting, decryption, and authentication). It has several main characteristics, JFDA: (1) accomplishes fingerprinting in the encryption domain to preserve privacy and prevent encrypted data from being tampered without additional hash code/digest, (2) prevents tampering attack on the decrypted data to ensure the fidelity of the fingerprinted data, (3) makes user subscribing to a visual media be an examiner to authenticate the same visual media over the Internet. The effectiveness of the proposed method is confirmed by experimental results.

3D-Based Unattended Object Detection Method for Video Surveillance

Inspired by 2D GrabCut for still images, this paper proposes automated abandoned object segmentation by introducing 3D GrabCut in surveillance scenario. This allows the method to produce precise object extraction without needing user intervention. Both RGB and depth input are utilized to build abandoned object detector which can resist to shadow and brightness changes. We performed the indoor experiments to show that our system obtains an accurate detection and segmentation. Both quantitative and qualitative measurements are provided to analyze the result.

Rain streak removal based on non-negative matrix factorization

A rain streak in an image can degrade visual quality of that image to the human eye. Unfortunately, removing the rain streak from a single image represents a very challenging task. In this paper, a single image rain removal process based on non-negative matrix factorization is proposed. First, the rain image is broken down into a low-frequency and high-frequency part by a Gaussian filter. Therefore, the rain component, which lies mostly in the middle frequency range, can be discarded in high and low frequency domains. Next, non-negative matrix factorization (NMF) method is applied to deal with the rain streak in the low frequency domain. Finally, Canny edge detection and block copy strategy are performed separately to remove the rain component in the high frequency domain to improve image quality. In comparison with state-of-the-art approaches, the proposed method achieves competitive results without the need for an extra image database to train the dictionary.

Coding unit complexity-based predictions of coding unit depth and prediction unit mode for efficient HEVC-to-SHVC transcoding with quality scalability

Abstract To support good video quality of experiences in heterogeneous environments, transcoding an existed HEVC (high efficiency video coding) video bitstream to a SHVC (scalability extension of HEVC) bitstream with quality scalability is highly required. A straightforward way is to first fully decode the input HEVC bitstream and then fully re-encode it with the SHVC encoder, which requires a tremendous computational complexity. To solve the problem, in this paper, a coding unit complexity (CUC)-based prediction method for predictions of CU (coding unit) depth and PU (prediction unit) mode for efficient HEVC-to-SHVC transcoding with quality scalability is proposed to significantly reduce the transcoding complexity. The proposed method contains two prediction techniques, including (i) early termination and (ii) adaptive confidence interval, and predicts the CU depth and PU mode relying on the decoded information from the input HEVC bitstream. Experimental results have shown that the proposed method significantly outperforms the traditional HEVC-to-SHVC method by 74.14% on average in reductions of encoding time for SHVC enhancement layer.

Robust techniques for abandoned and removed object detection based on Markov random field

A novel framework for detecting abandoned objects with automatic GrabCut is presented.The Background (BG) distribution is constructed with dual Gaussian mixtures.Our system can obtain more robust results for CAVIAR, PETS2006 & CDnet 2014 datasets. This paper presents a novel framework for detecting abandoned objects by introducing a fully-automatic GrabCut object segmentation. GrabCut seed initialization is treated as a background (BG) modelling problem that focuses only on unhanded objects and objects that become immobile. The BG distribution is constructed with dual Gaussian mixtures that are comprised of high and low learning rate models. We propose a primitive BG model-based removed object validation and Haar feature-based cascade classifier for still-people detection once a candidate for a released object has been detected. Our system can obtain more robust and accurate results for real environments based on evaluations of realistic scenes from CAVIAR, PETS2006, CDnet 2014, and our own datasets.