Remarkable progress has been achieved for salient object detection based on deep learning. However, most of the previous works have the issues of how to extract more effective information from scale-varying data and how to improve the boundary quality. In this paper, we propose the multi-scale graph convolutional interaction network (MGCINet), which consists of the feature interaction module (FIM), the feature aggregation module (FAM), and the residual refinement module (RRM). FIMs fuse interactive features from neighboring scales. Based on two-layers graph convolutional network, FAMs aggregate scale-specific information by graph nodes interaction. RRMs optimize the coarse saliency maps with blurred boundaries by U-net residual blocks. In addition, we propose multi-scale weighted structural loss to assign different weights to pixels while focusing on image structure at various scales. Experiments show that our method outperforms the state-of-the-arts on five benchmark datasets under different evaluation metrics.

Virtual reality based preoperative planning for Minimally Invasive Vascular Intervention is useful, not only for increasing the success rate of operation, but also used as a training tool for improving doctors' skills. In this paper we present an interactive 3D preoperative planning and training system with haptic device. In this system, we present an intelligent trajectory planning algorithm for searching an optimal path automatically along the centerline in two ways: from the suitable inserting point to the specific target location or to the most of objectives. Also, for the purpose of interactive training, we connect the haptic device to the end of guide wire and propose an algorithm that enables the simulator to model guide wire and catheter insertions realistically through essential operations i.e. pushing, pulling and twisting actions. We demonstrate experiment results to show that the 3D preoperative planning and training system is usable for simulating guide wire insertion procedures with complex blood vessel structures.

The fusion of object and scene plays an important role in image editing field, especially in the film production process. Poisson image editing technique is widely used in the object-scene fusion and a new method based on IHS transform has also been offered recently. Unfortunately, both of these two means might cause color distortion. Through introducing the SFIM technique and combining with IHS transform, this paper proposes a new algorithm based on IHS transform and SFIM for the fusion of object and scene. It utilizes the SFIM technique to fuse the intensity under the IHS color space. Subjective quality evaluation and objective quality assessment data of comparative fusion experiment results show that the new algorithm not only can reduce the color distortion well and achieve better fusion result than the Poisson fusion scheme and the standard IHS transform fusion scheme in the application of object-scene fusion, but also performs fast and is more robust.

Multimedia data of huge amount gets involved into people's daily life, bringing us a very important issue of efficiently managing video collections. Semantic content based on video retrieval is most effective for finding information and actual application. Of the researches of video retrieval, Bag-of-features (BoF) deriving from local key points has recently appeared promising for visual classification. This paper presents a method of video semantic annotation based on BoF. First, video clips are segmented into shots and shot key frames are extracted. Then it constructs a visual vocabulary to describe BoF through the clustering of key point features. Finally, the key frame is described as a feature vector according to the presence or count of each visual word. The feature vector forms the classifier under Support Vector Machines (SVM) for semantic annotation. We test performance of BoF on movie video and TRECVID-2007 datasets. Our experiment generates competitive performance compared to the state-of-the-art techniques.

A virtual reality (VR) based training system for Minimally Invasive Vascular Surgery can be a very useful training tool for improving skills and reducing errors in operation. Computer vision techniques have the potential to be incorporated into a VR based training system for developing low cost, high accuracy and flexible systems in this area. In this paper, we present an interactive 3D training system that uses stereo vision to capture hand movements as the input operations for the system. The standard operations i.e. pushing, pulling and twisting are captured with stereo vision based on the improved Camshift tracking algorithm and parallel alignment model theory to acquire hand gestures information. We present a new approach to calculate virtual pushing/pulling force and turning angle as extra inputs for understanding these essential operations. In addition, an algorithm that enables the simulator to model guide wire and catheter insertions realistically is presented through these basic actions. The experiment results demonstrate that stereo vision based training system is useful and effective for simulating guide wire insertion procedures with low system cost and flexible operations.

The guidance of attention helps the human vision system (HVS) to detect and recognize objects rapidly. In this paper, we propose a bottom-up saliency algorithm based on sparse coding theory. Sparse coding decomposes the inputs into two parts, codes and residual. From the viewpoint of biological vision and information theory, the coding length is closely related to the local complexity while the residual is closely related to the uncertainty. The proposed algorithm defines the weighted residual using sparse coding length as saliency. By multiplying the L0 norm of sparse codes and the residual, a saliency map is obtained. The performance of the proposed method is evaluated using ROC curves with two different scale datasets and is compared with state-of-the-art models. Our algorithm outperforms all other methods and the results indicate a robust and accurate saliency.

Abstract Guidewire insertion is an imperative task of minimally invasive medical procedures. During the procedure, surgeons need to steer long flexible thin wires through patient's blood vessels to reach a clinical target. In this paper, we present a novel approach to model haptics of guidewire insertion process for training simulation. The algorithm also allows for the analysis of the insertion process through subtle physical behaviours of guidewires via force feedbacks. The method includes a 6‐DoF dynamic coupling between a rigid body, i.e. the virtual tool and the deformation of the wire simulated as an elastic rod. Instead of using the frictional contact force or the acceleration of the guidewire tip for haptic feedbacks, we compute constrained forces by directly connecting the virtual tool to the end of the guidewire. Therefore, the coupling scheme transmits haptic interactions through constrained dynamics between the virtual tool and the guidewire. Both positional and rotational control modes are implemented and evaluated with respect to the dynamics of the guidewire, user inputs and feedback forces. Experiments highlight the usability of our algorithm for an insertion procedure simulation with complex blood vessel structures. Copyright © 2011 John Wiley & Sons, Ltd.

Video shot detection is an important contemporary problem since it is the first step toward automatic indexing, content based video retrieval and many other different applications. A novel shot boundary detection using wavelet and Support Vector Machine is proposed in this paper. Shot boundary detection algorithms work by extracting the color and the edge in different direction from wavelet transition coefficients. A multi-class support vector machine (SVM) classifier is used to classify the video shot into three categories: cut transition(CT), gradual transition(GT) and normal sequences (NF). To enhance the robustness of the algorithm, we form the feature vector from all frames within a temporal window. Numerical experiments using a variety of videos demonstrate that our method is capable of accurately detecting and discriminating shot transitions in videos with different characteristics.

Recently, keypoint descriptors such as Scale Invariant Feature Transform (SIFT) have been proved promising in similarity retrieval of images, which adopts matching score as similarity. However, the matching score is easy to be decreased once there are little variances between image details, and hence lead to low retrieval performance. In this paper, we propose a novel retrieval approach that improves the matching score with reduced time of matching by Kernel-based Fuzzy C-Means clustering (KFCM), which proves to be a better trade-off between matching and retrieval precision. Experiments conducted on three representative image databases show that our retrieval approach is surprisingly effective, outperforming the SIFT based method, not only in object-based image retrieval but also for searching scenes with similar semantic.

Shot boundary detection is an important fundamental process in video analysis. A novel shot boundary detection is proposed in this paper. To improve the performance of the algorithm and reduce the computational cost, frames that are clearly not shot boundaries are first removed from the original video. After that, new features are proposed to capture the changing statistics of different kinds of shot transitions so as to identify, not only abrupt shot transitions, but also gradual transitions accordingly. At last, use different algorithms for different kinds of shot transitions to help us to get a better solution for shot boundary detection problem. Numerical experiments in a variety of videos demonstrate that our method is capable of accurately detecting shot transitions, and could greatly reduce the computational cost.

Blotch is a typical artifact in old films and the detection of them is an important step in film restoration. The existing simplified rank-ordered difference detector achieves higher detection rates by reducing the value of threshold. However, the corresponding higher number of false alarms is undesirable. To maximize the ratio between correct detections and false alarms, this paper proposes an improved blotch detector based on adaptive multi- threshold. According to different objects of blotches, the proposed detector can achieve the most appropriate threshold by convergence confinement. Meanwhile, texture matching is introduced to avoid the possible deviation caused by motion vector estimation in the regions with blotches. Performance evaluation is taken to the image sequences with both real blotches and artificially corrupted ones. The experimental results indicate higher correct detection rates and fewer false alarms simultaneously.