A new Fractal Series Expansion based enhancement model for license plate recognition

License plate recognition is an emerging topic for real-time applications in smart city development because of automatic systems for toll fee-paying, traffic controlling, and vehicle detection. Speed of vehicles, unpredictable weather conditions such as night/low light/limited light images, and capturing images at different angles make recognition harder. This paper presents a new Fractal Series Expansion (FSE) model for license plate image enhancement. The proposed FSE model is justified because it estimates the high probability for the pixels which represent the license plate compared to the pixels which represent background irrespective of the above challenges, resulting in enhanced image. Besides, since the FSE model considers local information for estimating probability, the model has the ability to tackle non-uniform degradations as well as distortion affected multiple adverse factors. In addition to qualitative results, to validate the effectiveness of the proposed enhancement, quantitatively, recognition rates of the different methods before and after enhancement are computed. For this purpose, we have considered different datasets like dataset of Night License Plate Images (NLPI), which consists of images captured in the night and low lights environment, the UCSD benchmark dataset which provides poor and high quality day license plate images, etc. It is noted that recognition results after enhancement is higher than that of before enhancement, and hence our enhancement is useful and effective.     

Robust motion estimation for night-shooting videos using dual-accumulated constraint warping

This paper introduces a novel concept of dual-accumulated constraint projection warping, as a robust and efficient motion estimation solution for night video stabilization. Small imaging-sensors used in compact hand-held cameras become very prone to noise and blur under low illumination condition. Restricted lighting results in dark boundaries and degrades textural information of the frame. Presence of these combined textural artifacts makes night-shooting a hard problem for accurate motion estimation. At poor lighting, local intensity variations result in failure of inter-frame feature or block matching correspondence. In the proposed technique, use of projection ensures accuracy under local perturbations, noise and blur conditions, while dual-accumulation eliminates the effect of dark-regions adding robustness to night-shooting condition. Efficiency of the proposed algorithm over the existing motion estimation techniques is tested and verified over different categories of night shooting videos. In addition to night video stabilization the proposed scheme also performs well under normal illumination.     

注意力模型指导下的视频质量评价方法

在视频质量评价方法中,常常需要对人眼视觉系统做出合理的假设,其中注意力模型就是一个很重要的因素。提出了一种在注意力模型指导下的视频质量评价方法,在图像帧的质量评价中加入了显著性区域信息,使之更能符合人眼视觉特性,并兼顾了视频中的运动信息,在一定程度上提高了客观质量评价方法的性能。     

低照度环境下视频增强技术

在低照度环境下,摄像机捕捉到的夜间视频质量较差,常出现光照不足、对比度低、模糊不清和颜色偏移等问题,影响了视频的判读和理解。针对夜间视频存在的问题,提出不同时段空间背景融合技术和根据Retinex理论利用三边滤波器提取亮度图像的照度分量并结合Sigmiod 非线性拉伸函数对反射分量进行增强处理以突出细节达到图像增强的目的。经实验证明,提出的算法能够提高低照度夜间视频的整体视觉效果,图像的亮度、对比度、清晰度得到改善,突出了视频图像细节,保留了视频重要内容,增强结果自然清晰,避免了图像失真等问题,解决了夜间视频增强中常出现的光晕、鬼影、颜色偏移等问题,便于视频的判读与分析。     

Combining scene model and fusion for night video enhancement

This paper presents a video context enhancement method for night surveillance. The basic idea is to extract and fuse the meaningful information of video sequence captured from a fixed camera under different illuminations. A unique characteristic of the algorithm is to separate the image context into two classes and estimate them in different ways. One class contains basic surrounding scene information and scene model, which is obtained via background modeling and object tracking in daytime video sequence. The other class is extracted from nighttime video, including frequently moving region, high illumination region and high gradient region. The scene model and pixel-wise difference method are used to segment the three regions. A shift-invariant discrete wavelet based image fusion technique is used to integral all those context information in the final result. Experiment results demonstrate that the proposed approach can provide much more details and meaningful information for nighttime video.     

Extraction of high-resolution frames from video sequences

The human visual system appears to be capable of temporally integrating information in a video sequence in such a way that the perceived spatial resolution of a sequence appears much higher than the spatial resolution of an individual frame. While the mechanisms in the human visual system that do this are unknown, the effect is not too surprising given that temporally adjacent frames in a video sequence contain slightly different, but unique, information. This paper addresses the use of both the spatial and temporal information present in a short image sequence to create a single high-resolution video frame. A novel observation model based on motion compensated subsampling is proposed for a video sequence. Since the reconstruction problem is ill-posed, Bayesian restoration with a discontinuity-preserving prior image model is used to extract a high-resolution video still given a short low-resolution sequence. Estimates computed from a low-resolution image sequence containing a subpixel camera pan show dramatic visual and quantitative improvements over bilinear, cubic B-spline, and Bayesian single frame interpolations. Visual and quantitative improvements are also shown for an image sequence containing objects moving with independent trajectories. Finally, the video frame extraction algorithm is used for the motion-compensated scan conversion of interlaced video data, with a visual comparison to the resolution enhancement obtained from progressively scanned frames.     

Speed up of Video Enhancement based on Human Perception

This paper presents SUVEHP (speed up of video enhancement based on human perception), a human perception-based model oriented to reduce the computational time of digital video restoration. In particular, two specific hypothesis tests able to classify degraded frame regions are proposed. Classification is performed in agreement with regions visual significance in order to enable or inhibit motion compensated enhancement. The level of the proposed hypothesis tests is theoretically assessed. Moreover, extensive experimental results on video sequences affected by additive Gaussian noise show that SUVEHP speeds up some standard motion compensated denoisers up to 60%, preserving or even slightly increasing both the objective and subjective visual quality of the restored sequences.     

Drift controlled scalable wavelet based video coding in the overcomplete discrete wavelet transform domain

Traditional video coders use the previous frame to perform motion estimation and compensation. Though they are less complex and have minimum coding delays, these coders lose their efficiency when subjected to scalability requirements. Recent 3D wavelet coders using lifting schemes offer high compression efficiency and scalability without significant loss in performance. The main drawback of 3D coders is that they process several frames at a time. This introduces additional delay, which makes them less suitable for real time applications.In this work, we propose a novel scheme to minimize drift in scalable wavelet based video coding, which gives a balanced performance between compression efficiency and reconstructed quality with less drift. Our drift control mechanism maintains two frame buffers in the encoder and decoder; one that is based on the base layer and one that is based on the base plus enhancement layers. Drift control is achieved by switching between these two buffers for motion estimation and compensation. Our prediction is initially based on the base plus enhancement layers buffer, which inherently introduces drift in the system if a part of the enhancement layer is not available at the receiver. A measure of drift is computed based on the channel information and a threshold is set. When the measure exceeds the threshold, i.e., when drift becomes significant, we switch the prediction to be based on the base layer buffer, which is always available to the receiver. We also developed an adaptive scheme with additional computation overhead at the encoder to decide the switching instance. The performance of the threshold case that needs fewer computations is comparable with the adaptive scheme. Our coder offers high compression efficiency and sustained video quality for variable bit rate wireless channels. This proves that we need not completely eliminate drift and decrease compression efficiency to get better received video quality.     

Rate control for consistent visual quality of H.264/AVC encoding

In this paper, a novel rate control scheme with sliding window basic unit is proposed to achieve consistent or smooth visual quality for H.264/AVC based video streaming. A sliding window consists of a group of successive frames and moves forward by one frame each time. To make the sliding window scheme possible for real-time video streaming, the initial encoder delay inherently in a video streaming system is utilized to generate all the bits of a window in advance, so that these bits for transmission are ready before their due time. The use of initial encoder delay does not introduce any additional delay in video streaming but benefits visual quality as compared to traditional one-pass rate control algorithms of H.264/AVC. Then, a Sliding Window Buffer Checking (SWBC) algorithm is proposed for buffer control at sliding window level and it accords with traditional buffer measurement of H.264/AVC. Extensive experimental results exhibit that higher coding performance, consistent visual quality and compliant buffer constraint can be achieved by the proposed algorithm.     

灰度校正在红外序列图像拼接中的应用

为满足红外图像无缝拼接的需要,提出了一种基于红外序列图像的灰度非均匀性校正算法.该算法利用灰度非均匀区域的相对稳定性,通过对拍摄的大量红外序列图像求平均,获得相机灰度校正的模板图像.然后利用此模板对各帧图像进行校正,实现在同一幅度照射下各像素灰度的一致性.最后利用由HJRG-001型红外热像仪获得的红外视频图像序列进行...     

Real-time multimodal retinal image registration for a computer-assisted laser photocoagulation system

An algorithm for the real-time registration of a retinal video sequence captured with a scanning digital ophthalmoscope (SDO) to a retinal composite image is presented. This method is designed for a computer-assisted retinal laser photocoagulation system to compensate for retinal motion and hence enhance the accuracy, speed, and patient safety of retinal laser treatments. The procedure combines intensity and feature-based registration techniques. For the registration of an individual frame, the translational frame-to-frame motion between preceding and current frame is detected by normalized cross correlation. Next, vessel points on the current video frame are identified and an initial transformation estimate is constructed from the calculated translation vector and the quadratic registration matrix of the previous frame. The vessel points are then iteratively matched to the segmented vessel centerline of the composite image to refine the initial transformation and register the video frame to the composite image. Criteria for image quality and algorithm convergence are introduced, which assess the exclusion of single frames from the registration process and enable a loss of tracking signal if necessary. The algorithm was successfully applied to ten different video sequences recorded from patients. It revealed an average accuracy of 2.47 ± 2.0 pixels (～23.2 ± 18.8 μm) for 2764 evaluated video frames and demonstrated that it meets the clinical requirements.     

Adaptive color image processing and recognition for varyingbackgrounds and illumination conditions

The paper presents a fuzzy-based method for recognizing color objects in a complex background under varying illumination. Fuzzy rules are generated using a fuzzy associative memory (FAM) training method to cope with chromatic distortion. The color model used is the hue, saturation, and value (HSV) color model. The authors propose a unique adaptive fuzzy system, motivated by the human vision system's color constancy, in order to accommodate varying background color and illumination conditions, as well as incorrect focus of the camera. This adaptive system can adjust the fuzzy rules dynamically based on the properties of surrounding pixels in order to make a decision. The proposed method is tested on a two-hour video tape captured by a GPSVan, in which real-world scenes may have incorrect video camera focus, color distortions, and varying illumination conditions. Experimental results are reported and analyzed     

Enabling stereoscopic high dynamic range video

Stereoscopic and high dynamic range (HDR) imaging are two methods that enhance video content by respectively improving depth perception and light representation. A large body of research has looked into each of these technologies independently, but very little work has attempted to combine them due to limitations in capture and display; HDR video capture (for a wide range of exposure values over 20 f-stops) is not yet commercially available and few prototype HDR video cameras exist. In this work we propose techniques which facilitate stereoscopic high dynamic range (SHDR) video capture by using an HDR and LDR camera pair. Three methods are proposed: one based on generating the missing HDR frame by warping the existing one using a disparity map; increasing the range of LDR video using a novel expansion operator; and a hybrid of the two where expansion is used for pixels within the LDR range and warping for the rest. Generated videos were compared to the ground truth SHDR video captured using two HDR video cameras. Results show little overall error and demonstrate that the hybrid method produces the least error of the presented methods.     

Smart selective encryption of H.264/AVC videos using confidentiality metrics

In the field of video protection, selective encryption (SE) is a scheme which ensures the visual security of a video by encrypting only a small part of the data. This paper presents a new SE algorithm for H.264/AVC videos in context-adaptive variable-length coding mode. This algorithm controls the amount of encrypted alternative coefficients (ACs) of the integer transform in the entropic encoder. Two visual quality measures, the peak signal-to-noise ratio (PSNR) and the structural similarity (SSIM), are used to measure the visual confidentiality level of each video frame and to control the amount of encrypted ACs. Moreover, a new psychovisual metric to measure the flickering is introduced, the so-called temporal structural similarity (TSSIM). This method can be applied on intra and inter frame video sequences. Several experimental results show the efficiency of the proposed method.     

基于红外探测技术的嵌入式智能监测平台研究

在实际照度较低的环境中，可见光波段的CCD摄像机获取的图象模糊不清，影响监测精度。而采用散射光小，穿透能力强的红外CCD，则可以显著改善图象质量，从理论上分析了Rayleigh散射，Mie散射，无选择散射对监测的影响，讨论了红外波段CCD的反射系数、透射系数与波长的关系。实验表明：监测采用红外波段可显著提高空间分辨率、穿透性，且能有效抑制光线散射造成的影响。     

SSIM-based Error Resilient Video Coding Over Packet-Switched Networks

The visual quality is a critical factor in prediction video coding over packet-switched networks. However, the traditional MSE-based error resilient video coding cannot correlate well with the perceptual characteristics of the human visual system (HVS). This paper proposes a structural similarity (SSIM) based error resilient video coding scheme to improve the visual quality of compressed videos over packet-switched networks. In the proposed scheme, a SSIM-based end-to-end distortion model is developed to estimate the perceptual distortion due to quantization, error concealment, and error propagation. Based on this model, an adaptive mode selection strategy is presented to enhance the communication robustness of compressed videos. Experiments show that the proposed scheme significantly improves the visual quality for H.264/AVC video coding over packet-switched networks.     

Fuzzy reasoning model to improve face illumination invariance

Enhancing facial images captured under different lighting conditions is an important challenge and a crucial component in the automatic face recognition systems. This work tackles illumination variation challenge by proposing a new face image enhancement approach based on Fuzzy theory. The proposed Fuzzy reasoning model generates an adaptive enhancement which corrects and improves non-uniform illumination and low contrasts. The FRM approach has been assessed using four blind-reference image quality metrics supported by visual assessment. A comparison to six state-of-the-art methods has also been provided. Experiments are performed on four public data sets, namely Extended Yale-B, Mobio, FERET and Carnegie Mellon University Pose, Illumination, and Expression, showing very interesting results achieved by our approach.     

Sun position estimation and tracking for virtual object placement in time-lapse videos

Realistic illumination of virtual objects placed in real videos is important in terms of achieving visual coherence. We propose a novel approach for illumination estimation on time-lapse videos and seamlessly insert virtual objects in these videos in a visually consistent way. The proposed approach works for both outdoor and indoor environments where the main light source is the Sun. We first modify an existing illumination estimation method that aims to obtain sparse radiance map of the environment in order to estimate the initial Sun position. We then track the hard ground shadows on the time-lapse video by using an energy-based pixel-wise method. The proposed method aims to track the shadows by utilizing the energy values of the pixels that forms them. We tested the method on various time-lapse videos recorded in outdoor and indoor environments and obtained successful results.     

微光图像随机瞬态激光增强技术研究

以改善微光电视图像质量和增加夜视系统所获取的战场信息量为目标,提出了微光图像随机瞬态增强技术。并设计了伪随机瞬态激光发射及近红外激光 视图像同步捕促控制电路。该技术能在现有条件下显著提高被动微成像系统输出图像对比度,提高了微光夜视 效视距。     

微光视频器件及其技术的进展

微光夜视技术作为当今拓展人眼夜间视觉感知的主要技术之一,在军事和民用领域都有广泛的应用。随着数字图像处理技术的发展,微光视频器件为通过图像处理进一步提升夜视图像质量,为与红外热成像的图像信息融合,为提高夜间对目标探测/识别和场景理解能力等方面提供了广泛空间,成为当前国内外夜视技术发展的重要方向之一。论文综述了微光视频器件发展,分析了电真空+固体微光视频成像器件(如像增强CCD/CMOS(ICCD/ICMOS)器件、电子轰击EBCCD/EBCMOS器件等)、全固体微光视频成像器件(如电子倍增CCD器件、超低照度CMOS器件等)的特点和发展趋势,并结合法国PHOTONIS公司的LYNX计划,对微光夜视技术的发展进行了分析和讨论。