基于类人视觉的多任务交通目标实时检测模型

针对复杂交通场景下单个模型无法同时对可行驶区域和交通目标进行统一检测和检测实时性较差的问题,本文中提出了一种基于类人视觉的多任务交通目标单阶段检测模型,实现了可行驶区域和车辆、行人的实时统一检测。首先建立类人视觉注意力机制进行监督,采用轻量化模型MobileNetV3作为骨架,接着利用特征金字塔的思想对可行驶区域进行检测,最后采用动态注意力算法和anchor-free思想对交通目标进行检测。实验结果表明,引入驾驶员人眼注意力机制明显提升了模型的精度和鲁棒性,模型在实车上平均运算速度达到了12帧/s。

NEW CORNER DETECTION ALGORITHM BASED ON MULTI-FEATURE SYNTHESIS

Corner detection is a chief step in computer vision. A new corner detection algorithm in planar curves is proposed. Firstly, from the human perception, two key characteristics are given as an amendment of the traditional corner properties. Based on the two properties, the concept of the fuzzy set is introduced into a detection. Secondly, the extracted-formulae of three groups including the features of the corner subject degree are derived. Through synthesizing the features of three groups, the judgments of the corner detection, location, and optimization are obtained. Finally, by using the algorithm the detection results of several examples and feature curves for some interested parts, as well as the detection results for the test images history in references are given. Results show that the algorithm is easily realized after adopting the fuzzy set, and the detection effect is very ideal.

A NEW IMAGE QUALITY ASSESSMENT BASED ON HVS

This letter proposes a new kind of image quality philosophy—Modulate Quality based on Fixation Points (MQFP) based on Human Visual System (HVS) model. Dissimilar to the former HVS-based quality assessment, the new measure emphasizes particularly on modeling the jumping phenomenon of human sight instead of modeling the visual perception of human. In other words, to model the HVS using fixation points and stay-frequency instead of Contrast Sensitive Function (CSF) etc. which models the visual perception of HVS. The experiment on various frequency-distortion images indicates that the new measure is correlated with the subjective judgment more than the former HVS-based measure and is a robust measure.

Image Hiding Algorithm in Discrete Cosine Transform Domain Based on Grey Prediction and Grey Relational Analysis

Traditional information hiding algorithms cannot maintain a good balance of capacity,invisibility and robustness.In this paper,a novel blind colour image information hiding algorithm based on grey prediction and grey relational analysis in the Discrete Cosine Transform(DCT) domain is proposed.First,this algorithm compresses the secret image losslessly based on the improved grey prediction GM(1,1)(IGM) model.It then chooses the blocks of rich texture in the cover image as the embedding regions using Double-dimension Grey Relational Analysis(DGRA).Finally,it adaptively embeds the compressed secret bits stream into the DCT domain mid-frequency coefficients,which are decided by those blocks' Double-Dimension Grey Correlation Degree(DGCD) and Human Visual System(HVS).This method can ensure an adequate balance between invisibility,capacity and robustness.Experimental results show that the proposed algorithm is robust against JPEG compression(46.724 6 dB when the compression quality factor is 90%),Gaussian noise(45.531 3 dB when the parameter is(0,0.000 5)) etc.,and it is a blind information hiding algorithm that can be extracted without an original carrier.

DCT based multipurpose watermarking technique for image copyright notification and protection

A multipurpose image watermarking technique based on DCT is proposed to notify and protect the copyright of digital products. In order to achieve this objective, the DCT coefficients of each image block are divided into two parts for embedding the visible and invisible watermarks. The visible watermark is embedded in each DC DCT coefficient and most of the AC DCT coefficients of every block, and the invisible watermark in the rest. Based on the characteristics of Human Visual System (HVS), the embedding strength of the visible watermark is varied in accordance with the underlying content of the host image. The invisible watermark is embedded in a quaternity of midrange frequencies. Experimental results show that the visible watermark is hard to remove and the invisible watermark is robust to common digital signal processing operations.

A FINE GRANULAR JOINT SOURCE CHANNEL CODING METHOD

An improved FGS (Fine Granular Scalability) coding method is proposed in this letter, which is based on human visual characteristics. This method adjusts FGS coding frame rate according to the evaluation of video sequences so as to improve the coding efficiency and subject perceived quality of reconstructed images. Finally, a fine granular joint source channel coding is proposed based on the source coding method, which not only utilizes the network resources efficiently, but guarantees the reliable transmission of video information.

Perceptual importance analysis for H.264/AVC bit allocation

The existing H.264/AVC rate control schemes rarely include the perceptual considerations.As a result,the im-provements in visual quality are hardly comparable to those in peak signal-to-noise ratio(PSNR).In this paper,we propose a perceptual importance analysis scheme to accurately abstract the spatial and temporal perceptual characteristics of video contents.Then we perform bit allocation at macroblock(MB)level by adopting a perceptual mode decision scheme,which adaptively updates the Lagrangian multiplier for mode decision according to the perceptual importance of each MB.Simulation results show that the proposed scheme can efficiently reduce bit rates without visual quality degradation.

Shadow detection combining characters of human vision

A shadow detection method using pulse couple neural network inspired by the characters of human visual system is proposed.More precisely,lateral inhibition of human vision and coefficient of variation are combined together to improve the pulse couple neural network.Shadow detection is considered to be a shadow region segmentation problem.Experiment shows that the presented method is consistent with human vision compared to shadow detection methods based on HSV and pulse couple neural network(PCNN) by both subjective and objective assessments.

A Visual Cultural Study of Pictorial Weekly in the Republican Period

Peter Burke once said, using images as historical evidence could not only stand as proof of political events, economic trend, and social structure, but also as an illustration of the history of daily life, material culture, mental state, and physical body. Photography is the extension of human vision, the appearance of which has changed the way in which people see the world, molded the subject identity of modernity, and participated in the social construction of visual modernity. To witness the history is not the only purpose of studying on photograph-based pictorials in the republican period, for which it is more important to provide visual reference for the construction of China＇s modernization, and to witness the multiplicity, mobility, and inner-diversity of modernity.

Semantic categorization of indoor places using CNN for mobile robot exploration

The ability of achieving a semantic understanding of workspaces is an important capability for mobile robot. A method is proposed to categorize different places in a typical indoor environment by using a Kinect sensors for mobile robot exploration. At first, the invariant feature based images stitching approach is adopted to form a panoramic image according to Kinect visual information, and the translation between Kinect depth information and obstacle distance information is performed to obtain virtual LIDAR data. Then, the semantic classifier is designed by using convolutional neural networks （CNN） for indoor place eategorization based on Kinect visual observations with panoramic view. At last, a frontier-based exploration method is applied to carry out indoor autonomous exploration of mo- bile robots, which integrates the CNN-based categorization approach. The proposed method has been implemented and tested on a real robot, and experiment results demonstrate the approach effective- ness on solving the semantic categorization problem for mobile robot exploration.

Prioritization of liver MRI for distinguishing focal lesions

Liver cancer is one of the leading causes of cancer-related mortality worldwide.Magnetic resonance imaging(MRI) is a non-invasive imaging technique that is often used by radiologists for diagnosis and surgical planning.Analysis of a large amount of liver MRI data for each patient limits the radiologist's efficiency and may lead to misdiagnoses.The redundant MRI data,especially from dynamic contrast enhanced(DCE) sequences,is also a bottleneck in transmitting the images via the internet or PACS for remote consultancy in a reasonable amount of time.This study included 25 patients(aged between 20 and 70years) with liver cysts(seven cases),hemangiomas(eight cases),or hepatic cell carcinomas(10 cases).DCE T1 WI MRI was performed for all the patients.The diagnosis reference included typical MRI findings and post-surgery pathology.The methods were as follows:(i) MRI sequence pre-processing based on large vessels variation level set method to remove non-liver parts from MRI images;(ii) human visual model features(luminance,motion,and contour) extraction and fusion;(iii) anomaly-based MRI ranking;and(iv) methods assessment with the 25 patients' DCE MRI data.The prioritization methods applied to the DCE images could automatically assimilate and determine the content of the medical images,identifying the liver cysts,hemangiomas,and carcinomas.The average uniformity between radiologists and prioritization with the proposed method was 0.805,0.838,and0.818 for cysts,hemangiomas,and carcinomas,respectively,which indicates that the proposed method is an efficient method for liver DCE image prioritization.

A review of trachoma history in China: research, prevention, and control

Trachoma is one of the most widespread blinding eye diseases, which is harmful to human visual health. The efforts to prevent and control trachoma in China can be divided into three periods, i.e., highly epidemic period, research on pathogenesis and control of trachoma, and blinding trachoma elimination and epidemiological evaluation. In 1956, Prof. Feifan Tang and Xiaolou Zhang first discovered and isolated Chlamydia trachomatis, which clarified the cause of trachoma, and kick-started a fresh chapter in trachoma research, prevention, and control around the world. Although, the prevalence of trachoma differed in different areas, the average prevalence once exceeded 50% and was as high as 90% in some areas before and at early liberation of China. Therefore, the government-led efforts were made to comprehensively prevent and control trachoma, including development of National Plan for the Prevention and Control of Trachoma, nationwide screening and treatment of trachoma, implementation of National Patriotic Health Campaign and improvement of water supply and lavatories. After decades of effort, China reached the goal of eliminating blinding trachoma in 2015. China has gained remarkable achievements in the prevention and treatment of trachoma, making outstanding contributions toward the goal of eliminating trachoma worldwide. The research, prevention, and control of trachoma in China were reviewed in this paper.

A network-aware error-resilient method using prioritized intra refresh for wireless video communications

We propose a novel prioritized intra refresh method for the wireless video communication.The proposed method considers the characteristics of the human visual system,the error-sensitivity of the bitstream,and the state of the time-varying wireless channel jointly.An expected perceptual distortion model was used to adjust the intra refresh rate adaptively.This model consists of the perceptual weight map based on an attention model,the bit error probability map based on bitstream size,and the dynamic channel state information(CSI).Experimental results indicate that,compared with other intra refresh methods that consider only the content of the video or the CSI,the proposed method improves the average peak signal-to-noise ratio(PSNR) of the whole frame by about 0.5 dB,and improves the average PSNR of the attention-area by about 0.8 dB.

Generation of nonhuman primate retinitis pigmentosa model by in situ knockout of RHO in rhesus macaque retina

Retinitis pigmentosa(RP)is a form of inherited retinal degenerative diseases that ultimately involves the macula,which is present in primates but not in the rodents.Therefore,creating nonhuman primate(NHP)models of RP is of critical importance to study its mechanism of pathogenesis and to evaluate potential therapeutic options in the future.Here we applied adeno-associated virus(AAV)-delivered CRISPR/SaCas9 technology to knockout the RHO gene in the retinae of the adult rhesus macaque(Macaca mulatta)to investigate the hypothesis whether non-germline mutation of the RHO gene is sufficient to recapitulate RP.Through a series of studies,we were able to demonstrate successful somatic editing of the RHO gene and reduced RHO protein expression.More importantly,the mutant macaque retinae displayed clinical RP phenotypes,including photoreceptor degeneration,retinal thinning,abnormal rod subcellular structures,and reduced photoresponse.Therefore,we suggest somatic editing of the RHO gene is able to phenocopy RP,and the reduced time span in generating NHP mutant accelerates RP research and expands the utility of NHP model for human disease study.

A 3D video visual comfort evaluation method on the consistency of accommodation and convergence

With the development of three-dimensional(3D) technology, visual fatigue problems in 3D video have got more attention. In this paper, we combine the human vision characteristics and depth perception theory, and propose a 3D video visual comfort evaluation method on the consistency of accommodation and convergence, which evaluates the visual comfort from the quantitative perspective under different horizontal disparities and viewing distances. The experimental results show that the proposed evaluation method exhibits good consistency with the subjective assessment results.