Scene Change Detection Research Articles

An Adaptive Motion Estimation Based on the Temporal Subband Analysis

Motion Estimation is one of the key components in video coding like MPEG. In this paper, a new motion estimation scheme for a MPEG-like video coder is suggested. The proposed "adaptive motion estimation" scheme consists of five function blocks: temporal subband analysis (TSBA), extraction of temporal activity distribution (TAD), scene change detection (SCD), picture type replacement (PTR), and temporally adapted block matching algorithm (TABMA). All five function blocks are developed primarily based on the temporal subband analysis. Our new block matching algorithm TABMA is capable of controlling the size of block matching area searched. According to the significance of TAD, TABMA adjusts its nonuniform motion vector searching area. TABMA guarantees accurate and cost-effective performance. Also, newly proposed SCD and PTR together can prevent poor motion prediction for a video sequence containing abruptly changed scenes in it. As a result of that, SCD and PTR contribute to the reduction of overall computational loads, yet maintaining excellent coding quality.

Variable temporal-length 3-D discrete cosine transform coding

Three-dimensional discrete cosine transform (3-D DCT) coding has the advantage of reducing the interframe redundancy among a number of consecutive frames, while the motion compensation technique can only reduce the redundancy of at most two frames. However, the performance of the 3-D DCT coding will be degraded for complex scenes with a greater amount of motion. This paper presents a 3-D DCT coding with a variable temporal length that is determined by the scene change detector. Our idea is to let the motion activity in each block be very low, while the efficiency of the 3-D DCT coding could be increased. Experimental results show that this technique is indeed very efficient. The present approach has substantial improvement over the conventional fixed-length 3-D DCT coding and is also better than that of the Moving Picture Expert Group (MPEG) coding.

Efficient Automatic Text Location Method and Content-Based Indexing and Structuring of Video Database

An efficient automatic text detection and location method for video documents is proposed and its application for the content-based retrieval of video is presented and discussed. Target frames are selected at fixed time intervals from shots detected by a scene-change detection method. For each selected frame, segmentation by color clustering is performed around color peaks using a color histogram. For each color plane, text-lines are detected using heuristics, and the temporal and spatial position and the text-image of each text-line are stored in a database. Experimental results for text detection in video images and the performance of the method are reported for various video documents. A user interface for text-image based browsing is designed for direct content-based access to video documents, and other applications are discussed.

A New MPEG-2 Rate Control Scheme Using Scene Change Detection

We propose two new rate control schemes to improve MPEG-2 rate control in view of visual quality when scene changes happen. Two proposed schemes are characterized by real-time and non real-time improvement to reduce the impact of scene changes. We also propose a new target-bit prediction method using spatial activity of pictures and present a simple and efficient scene change detection scheme using signed difference of mean absolute difference (MAD). Computer simulation results show that the proposed real-time algorithm effectively alleviates visual quality degradation after scene changes. The proposed non real-time algorithm gives maximum 2 dB improvement in peak signal-to-noise ratio (PSNR) at a scene-changed picture, compared with MPEG-2 rate control scheme and it shows better quality than the real-time one.

Computational similarity based on chromatic barycenter algorithm

We propose in this paper a novel histogram-based chromatic barycenter algorithm for computing the similarity between images. The algorithm is simple, intuitive, and thus easy to implement. With its high precision and recall rates, the algorithm can be used as retrieval and scene change detection methods in very large video and image databases. When being used to process DCT based compressed data, the algorithm is even more efficient, as some of the time consuming decompression procedures can be skipped. This makes the algorithm an ideal tool for realtime and interactive multimedia applications with JPEG and MPEG data.

The Digital Wetgate: A Third-Generation Noise Reducer

This paper describes the development of noise-reduction technology and addresses its applications. First-generation noise reducers using linear filtering techniques such as recursive or transversal filters were designed for removing film grain noise or tape noise of analog VTRs. With the introduction of nonlinear median filtering techniques it became possible to conceal impulse-type noise such as film dust, randomly dispersed film scratches, or FM sparkles. — A third-generation noise reducer now has been developed by BTS. By the use of advanced techniques for error detection and motion adaption it is now possible to conceal large film dirt or fixed vertical film scratches — so-called tramline scratches. A wide range of new features especially designed for film reproduction, such as automatic pulldown and scene-change detection, provide great concealment power in the digital wetgate.

Rapid scene analysis on compressed video

Several rapid scene analysis algorithms for detecting scene changes and flashlight scenes directly on compressed video are proposed. These algorithms operate on the DC sequence which can be readily extracted from video compressed using Motion JPEG or MPEG without full-frame decompression. The DC images occupy only a small fraction of the original data size while retaining most of the essential "global" information. Operating on these images offers a significant computation saving. Experimental results show that the proposed algorithms are fast and effective in detecting abrupt scene changes, gradual transitions including fade-ins and fade-outs, flashlight scenes and in deriving intrashot variations.

A multi-layer video browsing system

The paper proposes an effective and efficient browsing system which is capable of representing the contents of a video sequence in a multi-layer manner. In this system, users can rapidly preview some preprocessed video shots, based on some simple scene change detection algorithm, to find out the particular video segments which are of interest. Because users just preview some video shots instead of examining all the video frames, this shot-based browsing method is superior to the conventional frame-based browsing one from the view points of the network bandwidth, user friendliness, and/or browsing efficiency. Based on the proposed browsing tool, a video-on-demand (VOD) prototype system has been implemented in the Communication and Multimedia Laboratory of National Taiwan University in an Ethernet LAN environment. >

012 Change detection in natural scenes using laser range measurements from a mobile robot

012 Change detection in natural scenes using laser range measurements from a mobile robot

Change Detection in Natural Scenes Using Laser Range Measurements from a Mobile Robot

The problem studied in this paper is to detect changes in both indoor scenes and natural outdoor scenes. The sensor is a scanning range measuring laser mounted on a mobile robot. The system should have the capability to detect when objects have been moved, have disappeared or when new objects have entered the area to be monitored. Also, the mobile robot must be able to navigate despite there are changes in the scene.The paper describes a method for simultaneous change detection and pose estimation. The algorithms are presently tested for outdoor scenes. The key tool is the distance transform

色割当の安定性を重視した動画像の限定色表示方式

In this paper, we propose a color quantization method for moving images which efficiently composes color quantized moving images with stable colors. In this method, the initial set of colors is chosen from the first frame, and used with high priority for the rest of the image sequence to achieve stable color allocation. To use the high correlation between subsequent frames, the color difference of each corresponding pixel between subsequent frames is first calculated and compared with the appropriate threshold. Then the pixels whose color differences are under the threshold are allocated to the same colors of the corresponding pixels of the preceding frame, and the colors of other pixels are reallocated. By this method, only differential operation is employed for most pixels.This method can also detect scene changes by monitoring the content of the “LUT”, so that it can deal with various kinds of moving images.Several experimental results in which the images of 224 colors are quantized to 16 colors reveal the effectiveness of the proposed method.

Low Bit Rate Motion Video Coder/Decoder For Teleconferencing

This paper describes motion video compression transmission for teleconferencing at a subprimary rate, i.e., at 384 kbits/s, including audio signal through the integrated services digital network (ISDN) HO channel. A subprimary rate video coder/decoder (codec), NETEC-XV, is available commercially that can operate at any bit rate (in multiples of 64 kbits/s) from 384 to 2048 kbits/s. In this paper, new algorithms are described that have been very useful in lowering the bit rate to 384 kbits/s. These algorithms are (1) separation of moving and still parts, followed by encoding of the two parts using different sets of parameters, and (2) scene change detection and its application to encoding parameter control. According to a brief subjective evaluation, the codec provides good picture quality even at a transmission bit rate of 384 kbits/s.