We recently introduced a new focal plane image compression algorithm that is implemented with 607 transistors inside every 4×4 pixel block of a CMOS imager, using conventional 0 35μm integration technology. This...
详细信息
ISBN:
(纸本)9781467312073
We recently introduced a new focal plane image compression algorithm that is implemented with 607 transistors inside every 4×4 pixel block of a CMOS imager, using conventional 0 35μm integration technology. This work focuses on preliminary results concerning the overall MTF of an imaging system in which the CMOS imager features focal-plane data compression based on DPCM and VQ with an overall bit rate below 0.94 bpp. Using bar-target pattern inputs, it is shown that details up to 2 cycles/cm are preserved in the decoded images. antonio@***
The traditional deep networks take raw pixels of data as input, and automatically learn features using unsupervised learning algorithms. In this configuration, in order to learn good features, the networks usually hav...
详细信息
ISBN:
(纸本)9781479957521
The traditional deep networks take raw pixels of data as input, and automatically learn features using unsupervised learning algorithms. In this configuration, in order to learn good features, the networks usually have multi-layer and many hidden units which lead to extremely high training time costs. As a widely used image compression algorithm, Discrete Cosine Transformation (DCT) is utilized to reduce image information redundancy because only a limited number of the DCT coefficients can preserve the most important image information. In this paper, it is proposed that a novel framework by combining DCT and deep networks for high speed object recognition system. The use of a small subset of DCT coefficients of data to feed into a 2-layer sparse auto-encoders instead of raw pixels. Because of the excellent decorrelation and energy compaction properties of DCT, this approach is proved experimentally not only efficient, but also it is a computationally attractive approach for processing high-resolution images in a deep architecture.
As medical imaging facilities move towards film-less imaging technology, robust imagecompression systems are starting to play a key role. Conventional storage and transmission of large-scale raw medical image dataset...
详细信息
ISBN:
(纸本)9781479988518
As medical imaging facilities move towards film-less imaging technology, robust imagecompression systems are starting to play a key role. Conventional storage and transmission of large-scale raw medical image datasets can be very expensive and time-consuming. Recently, we proposed a memory-assisted lossless image compression algorithm based on Principal Component Analysis (PCA). In this paper, we further improve the performance of the algorithm in two different directions: Firstly, we replace PCA with NMF (Non Negative Matrix Factorization). NMF has several advantages in representing images with an image-like basis, results in sparse factors, and provides better user control over iterations. Secondly, we expand the single-level model with a new multi-level decomposition/projection framework to further reduce entropy of residual images. Our experimental results on X-ray images confirm that both modifications provide significant improvements over the single level PCA based algorithm as well as existing non-memory based techniques.
This paper describes a novel approach to cope with driving scenarios in automated driving which are currently solved only by the driver's control. The approach presented in this paper is currently being implemente...
详细信息
This paper describes a novel approach to cope with driving scenarios in automated driving which are currently solved only by the driver's control. The approach presented in this paper is currently being implemented as a prototype to be used in our test fleet. It combines techniques well established in robotics like Simultaneous Localization And Mapping (SLAM) as well as end-to-end protection and image compression algorithms with big data technology used in a connected car context. This allows enhancing the positioning of individual vehicles in their Local Environment Model (LEM). This is the next step to overcome current dependencies to in-vehicle sensors by using additional cloud-based sensor processing to gain information.
暂无评论