Point Reg Net: Invariant Features for Point Cloud Registration Using in Image-Guided Radiation Therapy

In image-guided radiation therapy, extracting features from medical point cloud is the key technique for multimodality registration. This novel framework, denoted Control Point Net (CPN), provides an alternative to the common applications of manually designed keypoint descriptors for coarse point cloud registration. The CPN directly consumes a point cloud, divides it into equally spaced 3D voxels and transforms the points within each voxel into a unified feature representation through voxel feature encoding (VFE) layer. Then all volumetric representations are aggregated by Weighted Extraction Layer which selectively extracts features and synthesize into global descriptors and coordinates of control points. Utilizing global descriptors instead of local features allows the available geometrical data to be better exploited to improve the robustness and precision. Specifically, CPN unifies feature extraction and clustering into a single network, omitting time-consuming feature matching procedure. The algorithm is tested on point cloud datasets generated from CT images. Experiments and comparisons with the state-of-the-art descriptors demonstrate that CPN is highly discriminative, efficient, and robust to noise and density changes.

IMAGE DATABASE FOR PATTERN DESIGN SYSTEM

This paper discusses a pattern design system in textile industry,the establishment of an imagedatabase which is used to store various kinds of source materials for designers’ reference in order tospeed up design process.Pattern design image database (PDIDB) runs on the double-machine hardware system com-posed of ALTOS-986 and IBM PC/XT microcomputer.The former (host) manages imagedatabase,and the latter works both as a terminal to operate PDIDB and as an image processingstation to input,output,edit and display image data.PDIDB has two mainparts,the image storage management system and the image attributemanagement system and provides some functions,such as retrieval,deleting and updating.

A nowcasting model for the prediction of typhoon tracks based on a long short term memory neural network

It is of vital importance to reduce injuries and economic losses by accurate forecasts of typhoon tracks. A huge amount of typhoon observations have been accumulated by the meteorological department, however, they are yet to be adequately utilized. It is an effective method to employ machine learning to perform forecasts. A long short term memory（LSTM） neural network is trained based on the typhoon observations during 1949–2011 in China＇s Mainland, combined with big data and data mining technologies, and a forecast model based on machine learning for the prediction of typhoon tracks is developed. The results show that the employed algorithm produces desirable 6–24 h nowcasting of typhoon tracks with an improved precision.

Aerial-BiSeNet:A real-time semantic segmentation network for high resolution aerial imagery

The aircraft system has recently gained its reputation as a reliable and efficient tool for sensing and parsing aerial scenes.However,accurate and fast semantic segmentation of highresolution aerial images for remote sensing applications is still facing three challenges:the requirements for limited processing resources and low-latency operations based on aerial platforms,the balance between high accuracy and real-time efficiency for model performance,and the confusing objects with large intra-class variations and small inter-class differences in high-resolution aerial images.To address these issues,a lightweight and dual-path deep convolutional architecture,namely Aerial Bilateral Segmentation Network(Aerial-Bi Se Net),is proposed to perform realtime segmentation on high-resolution aerial images with favorable accuracy.Specifically,inspired by the receptive field concept in human visual systems,Receptive Field Module(RFM)is proposed to encode rich multi-scale contextual information.Based on channel attention mechanism,two novel modules,called Feature Attention Module(FAM)and Channel Attention based Feature Fusion Module(CAFFM)respectively,are proposed to refine and combine features effectively to boost the model performance.Aerial-Bi Se Net is evaluated on the Potsdam and Vaihingen datasets,where leading performance is reported compared with other state-of-the-art models,in terms of both accuracy and efficiency.

Adaptive segmentation based on multi-classification model for dermoscopy images

Segmentation accuracy of dermoscopy images is important in the computer-aided diagnosis of skin cancer and a wide variety of segmentation methods for dermoscopy images have been developed. Considering that each method has its strengths and weaknesses, a novel adaptive segmentation framework based on multi-classification model is proposed for dermoscopy images. Firstly, five patterns of images are summarized according to the factors influencing segmentation. Then the matching relation is established between each image pattern and its optimal segmentationmethod. Next, the given image is classified into one of the five patterns by the multi-classification model based on BP neural network. Finaily, the optimal segmentation method for this image is selected according to the matching relation, and then the image is effectively segmented. Experiments show that the proposed method delivers better accuracy and more robust segmentation results compared with the other seven state-of-the-art methods.

Hybrid fusion and interpolation algorithm with near-infrared image

Silicon-based digital cameras can record visible and near-infrared （NIR） information, in which the full color visible image （RGB） must be restored from color filter ar- ray （CFA） interpolation. In this paper, we propose a uni- fied framework for CFA interpolation and visible/NIR image combination. To obtain a high quality color image, the tra- ditional color interpolation from raw CFA data is improved at each pixel, which is constrained by the corresponding monochromatic NIR image in gradient difference. The ex- periments indicate the effectiveness of this hybrid scheme to acquire joint color and NIR information in real-time, and show that this hybrid process can generate a better color im- age when compared to treating interpolation and fusion sep- arately.

Easy modeling of realistic trees from freehand sketches

Creating realistic 3D tree models in a convenient way is a challenge in game design and movie making due to diversification and occlusion of tree structures. Current sketch-based and imagebased approaches for fast tree modeling have limitations in effect and speed, and they generally include complex parameter adjustment, which brings difficulties to novices. In this paper, we present a simple method for quickly generating various 3D tree models from freehand sketches without parameter adjustment. On two input images, the user draws strokes representing the main branches and crown silhouettes of a tree. The system automatically produces a 3D tree at high speed. First, two 2D skeletons are built from strokes, and a 3D tree structure resembling the input sketches is built by branch retrieval from the 2D skeletons. Small branches are generated within the sketched 2D crown silhouettes based on self-similarity and angle restriction. This system is demonstrated on a variety of examples. It maintains the main features of a tree： the main branch structure and crown shape, and can be used as a convenient tool for tree simulation and design.

A new skeleton based flying bird detection method for low-altitude air traffic management

In low-altitude air traffic management, non-cooperation targets are the greatest threat to security of low-flying aircraft. Among various aviation fatalities, flying bird is the main factor with the highest risk and directs economic losses amounted to nearly 10 billion US dollars each year.Therefore, Flying Bird Detection(FBD) has attracted considerable attention in low-altitude air traffic management. In this paper, we propose a skeleton based FBD method via describing bird motion information with a set of key poses. To overcome the variability of birds, the skeleton feature is selected as a relatively fixed and common characteristic for the pose appearance of flying bird. Based on the geometric topology among some key parts of bird body, a set of key poses can be described by some extracted skeleton features, which are used to represent the bird motion information. Aimed at robustly handling with the pose variations, multiple pose-specific classifiers are individually trained to learn the representative poses of the flying bird. At the detection stage,the flying bird skeleton features are combined with extracted key-pose sets to perform the flying bird classification task from each image. Afterwards, the key-frame pose-change set and the consistency of the classification results from sequent images are employed to validate the final detection results.Experiments on flying bird datasets demonstrate the effectiveness and efficiency of the proposed method.

Multi-view space object recognition and pose estimation based on kernel regression

The application of high-performance imaging sensors in space-based space surveillance systems makes it possible to recognize space objects and estimate their poses using vision-based methods. In this paper, we proposed a kernel regression-based method for joint multi-view space object recognition and pose estimation. We built a new simulated satellite image dataset named BUAA-SID 1.5 to test our method using different image representations. We evaluated our method for recognition-only tasks, pose estimation-only tasks, and joint recognition and pose estimation tasks. Experimental results show that our method outperforms the state-of-the-arts in space object recognition, and can recognize space objects and estimate their poses effectively and robustly against noise and lighting conditions.

Video stabilization based on modified invariant feature

To accurately estimate the motion parameters,especially for rotation,scale and transition,a new invariant feature descriptor is proposed based on simplified polar sampling.The Gaussian weighed regions in original version are replaced by the uniform weighted regions.Fast calculation of gradient-orientation histogram by means of integral map is adopted to improve the efficiency.Then a new method is proposed based on linear fitting of motion path and it can estimate the current frame position by local fitting parameters.The frame rate of stabilized output can reach 30 f/s,which gains notable im-provement compared with the general invariant feature methods such as SIFT and SURF.

A Novel Approach to Intra-operative Planning for Prostate Brachytherapy

This paper presents an efficient and stable algorithm to intra-operative planning for prostate brachytherapy. As a heuristic approach, the algorithm selects one seed at a step and iterates until predefined prostate volume is covered by prescribed dose. For each step, potential seeds are evaluated according to the ability to irradiate the target while sparing adjacent organs at risk. And its influence on dose homogeneity is also taken into account. Furthermore, a flexible mechanism is adopted to limit the number of used needles. The mechanism selects acceptable sub-optimal seed in existing needles instead of optimal seed that requires adding a new needle. The efficacy of algorithm is evaluated on five clinical cases. Compared with state-of-the-art methods,this algorithm is efficient and stable without the trial and error process of determining various parameters. These advantages make the algorithm suitable for intra-operative real-time treatment planning.