复杂环境下基于角点回归的全卷积神经网络的车牌定位

车牌定位是车牌识别系统中核心部分,具有较高的研究和应用价值。尽管近些年来该研究取得了很大的进展,但仍无法很好地解决低亮度、低分辨率和车辆倾斜等环境下的定位问题。本文提出了一种新的全卷积神经网络,通过回归车牌角点的方式准确地进行车牌定位。为了保证训练的有效性,对45 000幅含有车牌的图像进行人工标注。同时,对标注的图像随机进行平移、缩放、旋转和加噪,提高训练样本的数量和多样性。在本文构建的卡口图像数据集和复杂环境数据集上与两种方法进行了比较,验证了本文方法的有效性。     

城市交叉路口背景提取与车道标定算法

目的 为解决车辆对车道标记的遮挡问题,提出一种新的背景提取算法,同时基于透视变换实现了城市交叉路口的多车道标定。方法 首先,通过均值与帧间差分方法的融合,进行城市交叉路口的背景稳定与更新;然后,利用Canny算子及Hough直线检测得到各类直线;其次,基于透视变换、聚类分析和先验知识建立了车道线的筛选数学模型,实现了车道线标定;最后,通过实验对算法进行了验证。结果 采用10min长度、分辨率为2592×2048像素的某城市交叉路口实际监控视频进行交叉路口背景提取。本文算法的背景提取准确率比均值法和传统高斯混合模型法分别提升20%和30%左右,车道线标定也优于其他类似方法。结论 算法具有收敛速度快、准确率较高、稳定性较好等特点,在车流量大时可快速更新并消除车辆虚影,适用于光照条件正常的城市交叉种口的车道线标定。     

Letter: Solution‐processed flexible zinc‐tin oxide thin‐film transistors on ultra‐thin polyimide substrates

In this letter, solution‐processed flexible zinc‐tin oxide (Z_0.35T_0.65O_1.7) thin‐film transistors with electrochemically oxidized gate insulators (AlOx:Nd) fabricated on ultra‐thin (30 µm) polyimide substrates are presented. The AlOx:Nd insulators exhibited wonderful stability under bending and excellent insulating properties with low leakage current, high dielectric constant, and high breakdown field. The device exhibited a mobility of 3.9 cm²/V · s after annealing at 300 °C. In addition, the flexible device was able to maintain the electricity performance under various degrees of bending, which was attributed to the ultra‐thin polyimide substrate.     

Efficient near-duplicate image detection with a local-based binary representation

Efficient near-duplicate image detection is important for several applications that feature extraction and matching need to be taken online. Most image representations targeting at conventional image retrieval problems are either computationally expensive to extract and match, or limited in robustness. Aiming at this problem, in this paper, we propose an effective and efficient local-based representation method to encode an image as a binary vector, which is called Local-based Binary Representation (LBR). Local regions are extracted densely from the image, and each region is converted to a simple and effective feature describing its texture. A statistical histogram can be calculated over all the local features, and then it is encoded to a binary vector as the holistic image representation. The proposed binary representation jointly utilizes the local region texture and global visual distribution of the image, based on which a similarity measure can be applied to detect near-duplicate image effectively. The binary encoding scheme can not only greatly speed up the online computation, but also reduce memory cost in real applications. In experiments the precision and recall, as well as computational time of the proposed method are compared with other state-of-the-art image representations and LBR shows clear advantages on online near-duplicate image detection and video keyframe detection tasks.     

Arithmetic coding using hierarchical dependency context model for H.264/AVC video coding

In this paper, a hierarchical dependency context model (HDCM) is firstly proposed to exploit the statistical correlations of DCT (Discrete Cosine Transform) coefficients in H.264/AVC video coding standard, in which the number of non-zero coefficients in a DCT block and the scanned position are used to capture the magnitude varying tendency of DCT coefficients. Then a new binary arithmetic coding using hierarchical dependency context model (HDCMBAC) is proposed. HDCMBAC associates HDCM with binary arithmetic coding to code the syntax elements for a DCT block, which consist of the number of non-zero coefficients, significant flag and level information. Experimental results demonstrate that HDCMBAC can achieve similar coding performance as CABAC at low and high QPs (quantization parameter). Meanwhile the context modeling and the arithmetic decoding in HDCMBAC can be carried out in parallel, since the context dependency only exists among different parts of basic syntax elements in HDCM.     

Feature aggregating hashing for image copy detection

Currently, research on content based image copy detection mainly focuses on robust feature extraction. However, due to the exponential growth of online images, it is necessary to consider searching among large scale images, which is very time-consuming and unscalable. Hence, we need to pay much attention to the efficiency of image detection. In this paper, we propose a fast feature aggregating method for image copy detection which uses machine learning based hashing to achieve fast feature aggregation. Since the machine learning based hashing effectively preserves neighborhood structure of data, it yields visual words with strong discriminability. Furthermore, the generated binary codes leads image representation building to be of low-complexity, making it efficient and scalable to large scale databases. Experimental results show good performance of our approach.     

Multi-label classification via learning a unified object-label graph with sparse representation

Automatic annotation is an essential technique for effectively handling and organizing Web objects (e.g., Web pages), which have experienced an unprecedented growth over the last few years. Automatic annotation is usually formulated as a multi-label classification problem. Unfortunately, labeled data are often time-consuming and expensive to obtain. Web data also accommodate much richer feature space. This calls for new semi-supervised approaches that are less demanding on labeled data to be effective in classification. In this paper, we propose a graph-based semi-supervised learning approach that leverages random walks and ? ₁ sparse reconstruction on a mixed object-label graph with both attribute and structure information for effective multi-label classification. The mixed graph contains an object-affinity subgraph, a label-correlation subgraph, and object-label edges with adaptive weight assignments indicating the assignment relationships. The object-affinity subgraph is constructed using ? ₁ sparse graph reconstruction with extracted structural meta-text, while the label-correlation subgraph captures pairwise correlations among labels via linear combination of their co-occurrence similarity and kernel-based similarity. A random walk with adaptive weight assignment is then performed on the constructed mixed graph to infer probabilistic assignment relationships between labels and objects. Extensive experiments on real Yahoo! Web datasets demonstrate the effectiveness of our approach.