Responses of some landscape trees to the drought and high temperature events during 2006 and 2007 in Yamaguchi,Japan

Extreme weather events were analyzed based on the meteorological data from the year of 1967 to 2007 for Yamaguchi, Japan. The responses from landscape trees were also investigated mainly by the analysis of image pixel and spectral reflectance. Results show that after the dry, hot and windy summer in 2007, many landscape trees in Yamaguchi City tended to respond the extreme weather events by reducing their leaf surface area and receiving less radiation energy. Premature leaf discoloration or defoliation appeared on some landscape tree species and leaf necrosis occurred on tip and margin of many Kousa dogwood (Cornus kousa) trees at unfavorable sites. Described by image pixel analysis method, the leaf necrotic area percentage (LNAP) of sampled dogwood trees averaged 41.6% and the sampled Sasanqua camellia (Camelia sasanqua) tree also showed fewer flowers in flower season of 2007 than that in 2006. By differential analysis of partial discolored crown, it presented a logistic differential equation of crown color for sweet gum (Liquidambar styraciflua) trees. It suggested that the persistent higher temperature and lower precipitation could be injurious to the sensitive landscape trees at poor sites, even in relative humid area like Yamaguchi.

A learning-based method to detect and segment text from scene images

This paper proposes a learning-based method for text detection and text segmentation in natural scene images. First, the input image is decomposed into multiple connected-components (CCs) by Niblack clustering algorithm. Then all the CCs including text CCs and non-text CCs are verified on their text features by a 2-stage classification module, where most non-text CCs are discarded by an attentional cascade classifier and remaining CCs are further verified by an SVM. All the accepted CCs are output to result in text only binary image. Experiments with many images in different scenes showed satisfactory performance of our proposed method.

Automatic character detection and segmentation in natural scene images

We present a robust connected-component (CC) based method for automatic detection and segmentation of text in real-scene images. This technique can be applied in robot vision, sign recognition, meeting processing and video indexing. First, a Non-Linear Niblack method (NLNiblack) is proposed to decompose the image into candidate CCs. Then, all these CCs are fed into a cascade of classifiers trained by Adaboost algorithm. Each classifier in the cascade responds to one feature of the CC. Proposed here are 12 novel features which are insensitive to noise, scale, text orientation and text language. The classifier cascade allows non-text CCs of the image to be rapidly discarded while more computation is spent on promising text-like CCs. The CCs passing through the cascade are considered as text components and are used to form the segmentation result. A prototype system was built, with experimental results proving the effectiveness and efficiency of the proposed method.

Recognition of Similar Weather Scenarios in Terminal Area Based on Contrastive Learning

In order to improve the recognition accuracy of similar weather scenarios(SWSs)in terminal area,a recognition model for SWS based on contrastive learning(SWS-CL)is proposed.Firstly,a data augmentation method is designed to improve the number and quality of weather scenarios samples according to the characteristics of convective weather images.Secondly,in the pre-trained recognition model of SWS-CL,a loss function is formulated to minimize the distance between the anchor and positive samples,and maximize the distance between the anchor and the negative samples in the latent space.Finally,the pre-trained SWS-CL model is fine-tuned with labeled samples to improve the recognition accuracy of SWS.The comparative experiments on the weather images of Guangzhou terminal area show that the proposed data augmentation method can effectively improve the quality of weather image dataset,and the proposed SWS-CL model can achieve satisfactory recognition accuracy.It is also verified that the fine-tuned SWS-CL model has obvious advantages in datasets with sparse labels.

High-extensible scene graph framework based on component techniques

In this paper, a novel component-based scene graph is proposed, in which all objects in the scene are classified to different entities, and a scene can be represented as a hierarchical graph composed of the instances of entities. Each entity contains basic data and its operations which are encapsulated into the entity component. The entity possesses certain behaviours which are responses to rules and interaction defined by the high-level application. Such behaviours can be described by script or behaviours model. The component-based scene graph in the paper is more abstractive and high-level than traditional scene graphs. The contents of a scene could be extended flexibly by adding new entities and new entity components, and behaviour modification can be obtained by modifying the model components or behaviour scripts. Its robustness and efficiency are verified by many examples implemented in the Virtual Scenario developed by Peking University.

A Fast Algorithm for Automated Image Mosaicing

This paper presents a fast image mosaic algorithm based on the characteristic of the edge grads. Unlike some previous algorithms, which require pure horizontal camera panning, this algorithm doesn＇t require constraints on how the image is taken. The algorithm can determine the matching regions of the two adjacent images by finding out the feature points and can piece up images bath horizontally and vertically. Experimental results show that this algorithm is effective.

A framework of region-based dynamic image fusion

A new framework of region-based dynamic image fusion is proposed. First, the technique of target detection is applied to dynamic images (image sequences) to segment images into different targets and background regions. Then different fusion rules are employed in different regions so that the target information is preserved as much as possible. In addition, steerable non-separable wavelet frame transform is used in the process of multi-resolution analysis, so the system achieves favorable characters of orientation and invariant shift. Compared with other image fusion methods, experimental results showed that the proposed method has better capabilities of target recognition and preserves clear background information.

Research on Gaussian distribution preprocess method of infrared multispectral image background clutter

This paper introduces a sliding-window mean removal high pass filter by which background clutter of infrared multispectral image is obtained. The method of selecting the optimum size of the sliding-window is based on the skewness-kurtosis test. In the end, a multivariate Gaussian distribution mathematical expression of background clutter image is given.