Objects are often constrained to lie on a known plane. This paper concerns the pose determination and recognition of vehicles in traffic scenes, which under normal conditions stand on the ground-plane. The ground-plane constraint reduces the problem of localisation and recognition from 6 dof to 3 dof.

The ground-plane constraint significantly reduces the pose redundancy of 2D image and 3D model line matches. A form of the generalised Hough transform is used in conjuction with explicit probability-based voting models to find consistent matches and to identify the approximate poses. The algorithms are applied to images of several outdoor traffic scenes and successful results are obtained. The work reported in this paper illustrates the efficiency and robustness of context-based vision in a practical application of computer vision.

Multiple cameras may be used to overcome the limitations of a single camera. Data fusion in the proposed algorithms is shown to be simple and straightforward.

Model-Based Localisation and Recognition of Road Vehicles

In order to reduce the computation load, many conventional fast block-matching algorithms have been developed to reduce the set of possible searching points in the search window. All of these algorithms produce some quality degradation of a predicted image. Alternatively, another kind of fast block-matching algorithms which do not introduce any prediction error as compared with the full-search algorithm is to reduce the number of necessary matching evaluations for every searching point in the search window. The partial distortion search (PDS) is a well-known technique of the second kind of algorithms. In the literature, many researches tried to improve both lossy and lossless block-matching algorithms by making use of an assumption that pixels with larger gradient magnitudes have larger matching errors on average. Based on a simple analysis, it is found that, on average, pixel matching errors with similar magnitudes tend to appear in clusters for natural video sequences. By using this clustering characteristic, we propose an adaptive PDS algorithm which significantly improves the computation efficiency of the original PDS. This approach is much better than other algorithms which make use of the pixel gradients. Furthermore, the proposed algorithm is most suitable for motion estimation of both opaque and boundary macroblocks of an arbitrary-shaped object in MPEG-4 coding.

/pdf/new-adaptive-partial-distortion-search-using-clustered-pixel-1y9sp3r0zc.pdf

New adaptive partial distortion search using clustered pixel matching error characteristic

Device for transmitting and/or storing signals presented thereto representing the textures of different areas of a video picture. The device includes a sampling stage for deriving a reference sample of the texture signals from a given picture area, and a coding stage for coding the reference sample signal as well as area signals representative of texture over the entire area from which the sample has been taken. The coded output signals of the coding stage may be transmitted by a transmission medium such as a communication channel and/or a store. A decoding stage then decodes the coded signals, and a texture synthesis stage uses the decoded sample signals to enhance the decoded area signals, thereby effectively achieving synthesis of a reproduction of the relevant picture area having a texture closely resembling the texture of such area of the original picture.

System for transmitting and/or storing signals corresponding to textured pictures

http://biorobotics.ri.cmu.edu/papers/sbp_papers/integrated2/perantonis_block_decomp_hough.pdf

Block decomposition and segmentation for fast Hough transform evaluation

In this paper, geometrical analysis is used to extract novel straight line segment features from the wings around the peaks of the Hough Transform (HT). Based on these features, a practical segment detection method is proposed which has the ability to determine complete straight line segment parameters including the location of the center, length, slope and the Euclidean distance to the origin. The proposed method does not rely on edge point verification in the image space, i.e., the complete set of segment features are determined only using the information embodied in the HT data. The proposed method can distinguish between highly collinear straight line segments. Segment detection is robust to disturbing edge points, especially ones collinear with the object. A predefined collinear segment resolution that provides a theoretical criterion to determine straight line contiguity is derived. Image processing and analysis experiments show consistent robust performance.

Collinear Segment Detection Using HT Neighborhoods

A new VQ-based image coding method, classified vector quantization using texture analysis (CVQ-TA) is proposed. The most notable differences between CVQ-TA and CVQ are: (1) the classification in CVQ-TA operates in the transform domain by means of texture analysis, and (2) product-code vector quantization is used to reduce the complexity increasing with the subblock size. Because of these characteristics, CVQ-TA can be applied for large block size (8*8 or 16*16), which is more efficient for block coding. Simulation results show that CVQ-TA can give a good visual perceptual quality. >

http://ieeexplore.ieee.org/iel5/143/3356/00112276.pdf

Classified vector quantization of images using texture analysis

In this paper, we present an efficient algorithm to reduce the computation cost of block matching algorithms for motion estimation in video coding Based on a new insight in block matching algorithms, we extend the successive elimination algorithm to the multi-level case By using the sum norms of the blocks and the subblocks with reduced sizes, tighter and tighter decision boundaries for eliminating the search positions can be obtained in a multi-level manner The efficiency of the proposed algorithm combined with full search algorithm and several fast search algorithms is verified by simulation results

Multi-level successive elimination algorithm for motion estimation in video coding

This paper presents a subband filter bank model of N subbands for orthogonally multiplexed QAM system with 2N subchannels. Then, a fast implementation algorithm using polyphase decomposition and discrete cosine transform (DCT) is derived from this model. Compared with the implementation method through discrete Fourier transform, only half the computation cost is needed. Finally, we give the adaptive equalization scheme based on subband adaptive filter theory, and its efficiency is verified by experiments.

Subband model and implementation of O-QAM system

A fast Dynamic Hough Transform which is used for line detection is proposed. It employs the 1D Hough clustering technique. The peak detection and interpretation of the parameter space are very easy, and the endpoints and the connectivity of the line segments can be determined conveniently. A large amount of memory space can also be saved. Only integer operations are required in this transform, and the number of operations is proportional to the number of edge points. Thus, the transform can be carried out very fast. The parallel implementation of the transform based on a transputer network is given in order to meet the needs of real-time applications. >

Detection of line segments using a fast dynamic Hough transform

The authors developed a new adaptive image coding technique using interpolative mixed vector quantization (VQ) which mixes the 2D discrete cosine transform (DCT) with VQ. A median filter is first used to eliminate fine noise while not smearing the edges. After subsampling, the image is encoded by an adaptive mixed VQ coding scheme. At the receiver, a finite-impulse-response (FIR) median hybrid filter is used to interpolate missing pixels after subsampling. Some simulation results are given. It was found that high-quality coded images were obtained at a bit rate from about 0.25 to 0.5 b.p.p. >

Z.Y. He

Papers

Classified vector quantization of images using texture analysis

Multi-level successive elimination algorithm for motion estimation in video coding

Subband model and implementation of O-QAM system

Detection of line segments using a fast dynamic Hough transform

An adaptive image coding technique using interpolative mixed VQ