Path planning is of essential importance for Unmanned Surface Vessels (USV). Lots of path planning algorithms have been proposed in the last few years, however these algorithms have high computational complexity. Therefore, these algorithms are time consuming and not suitable for online path planning. In this paper, a rapid path planning algorithm for USVs is developed. The proposed algorithm segments the searching space into three subspaces: starting subspace, end subspace and passing subspace. With consider the performances of USVs, our algorithm plans a path from the edge of the starting subspace to the end subspace. Therefore the computational complexity is dramatically decreased. The experiment results show that the proposed scheme is efficient to fulfill the path planning task.

Obstacle detection is of essential importance for Unmanned Surface Vehicles (USV). Although some obstacles (e.g., ships, islands) can be detected by Radar, there are many other obstacles (e.g., floating pieces of woods, swimmers) which are difficult to be detected via Radar because these obstacles have low radar cross section. Therefore, detecting obstacle from images taken onboard is an effective supplement. In this paper, a robust vision-based obstacle detection method for USVs is developed. The proposed method employs the monocular image sequence captured by the camera on the USVs and detects obstacles on the sea surface from the image sequence. The experiment results show that the proposed scheme is efficient to fulfill the obstacle detection task.

An object detection for vision-aided inventory counting is developed. The propose approach is simple to use and reduce the workload remarkably. Meanwhile, the approach count the items of interest almost in real time with an acceptable precision, which is desirable in inventory counting. The experiment results show that the proposed approach is efficient to fulfill the counting task.

Image alignment is a useful technique in many important research fields of computer vision. Among all the image alignment algorithms, Lucas-Kanade algorithm is one of the most widely used algorithms. During the past 30 years, a wide variety of extensions have been made to the original formulation and an unabridged Lucas-Kanade algorithm series has been formed. In this paper, we propose a novel method which can accelerate the convergence of Lucas-Kanade algorithm series. Based on the theory of strongly concave/convex function, we define the Strongly Concave/Convex Areas (SC/CA) of images. Through discarding the SC/CA, the iteration number of Lucas-Kanade algorithm series can be reduced without decreasing the precision. Finally, we present various experimental results that validate our method. These results also show that the proposed method is robust with the parameter used in detecting the SC/CA.

Histogram of collinear gradient-enhanced coding (HCGEC), a robust key point descriptor for multi-spectral image matching, is proposed. The HCGEC mainly encodes rough struc- tures within an image and suppresses detailed textural information, which is desirable in multi-spectral image matching. Experiments on two multi-spectral data sets demonstrate that the proposed descriptor can yield significantly better results than some state-of- the-art descriptors.

Growth stage information of field crops is not only an important basic data for analyzing the relationship between the crop growth process and the agrometeorological conditions, but it is also useful for various aspects of precision agriculture. Up to now, it is primarily obtained manually, which is time-consuming, labor-intensive, subjective and discontinuous. Therefore, a noninvasive method to note observations that also proves to be more efficient, continuous, and automatic is needed. At present, an alternative method based on computer vision has been widely used for monitoring crop growth status due to advantages linked to its low-cost, its intuitiveness and non-contact manner of data gathering it provides. However, little research has been done to improve close observation of different growth stages of field crops using digital cameras. To overcome the drawbacks caused by the current manual observation, a study was conducted to explore the application of computer vision technology for the automatic detection technology of two critical growth stages of maize (emergence and three-leaf stage). In order to identify the growth stages, the first task is to extract the plants from images properly. According to complex factors on farm fields, we proposed a novel crops segmentation method (AP-HI) which is robust and not sensitive to the challenging variation of outdoor luminosity and complex environmental elements. It has laid the foundation for subsequent studies. By virtue of the AP-HI, two automatic detection methods based on imaging were investigated for the two critical growth stages of maize. The former method uses the spatial distribution feature to judge accurately whether the field crop has reached the emergence stage or not. The latter uses the skeleton endpoint to characterize the leaf of seedling and transforms a matter of judgment into that of probability estimation, which leads to the final conclusion. In order to verify the feasibility and validity of our proposed methods, the comparing experiments have been carried out. Five well-established algorithms were utilized to make comparison with AP-HI and its results showed that our method outperformed the other algorithms in yielding the highest performance of 96.68% with the lowest standard deviation of 237%. As for the two automatic detection methods, the crops of two experimental fields located in Zhengzhou, Henan and Taian, Shandong provinces in China were observed both with a human observer and by using automated routines to process images obtained from a camera. In determining the time at which a growth stage occurred, the proposed methods produced the similar results to the manual observation method. Overall, the automated methods can meet the demand for practical observation needed for agronomic modeling and in triggering action alerts to farmers. (C) 2013 Elsevier B.V. All rights reserved.

In this paper, a novel difficult prediction scheme for infrared building target recognition is developed. Our scheme can predict the difficulty of recognizing a designated target in advance, which is desirable in infrared building recognition. The experiment results show that our scheme is efficient to fulfill the prediction task and the prediction is consistent with the real recognition results.

This paper proposes a new approach to localize buildings from forward looking infrared (FLIR) images. The proposed approach can localize not only large buildings, but also small buildings. Furthermore, the proposed approach is also robust with those FLIR images degraded by clouds. This breakthrough is due to the following improvements: (1) the Histogram of Oriented Gradients approach is improved to match FLIR images with our templates; (2) a new kind of feature image is presented to reduce the difference between template and target; (3) we project 3D building models into images, with different colors on different sides, distinguishing those sides apart; (4) we generate templates which contain all buildings in the visual field. As a result, the FLIR images can be matched with the big templates at a high correct rate, and then target buildings can be localized. The experimental results show the superior performance of the proposed approach.

The detection of shadow is the first step to reduce the imaging effect that is caused by the interactions of the light source with surfaces, and then shadow removal can recover the vein information from the dark region. In this paper, we have presented a new method to detect the shadow in a single nature image with the saliency map and to remove the shadow. Firstly, RGB image is transferred to 2D module in order to improve the blue component. Secondly, saliency map of blue component is extracted via graph-based manifold ranking. Then the edge of the shadow can be detected in order to recover the transitional region between the shadow and non-shadow region. Finally, shadow is compensated by enhancing the image in RGB space. Experimental results show the effectiveness of the proposed method.

Recently the improved bag of features (BoF) model with locality-constrained linear coding (LLC) and spatial pyramid matching (SPM) achieved state-of-the-art performance in image classification. However, only adopting SPM to exploit spatial information is not enough for satisfactory performance. In this paper, we use hierarchical temporal memory (HTM) cortical learning algorithms to extend this LLC & SPM based model. HTM regions consist of HTM cells are constructed to spatial pool the LLC codes. Each cell receives a subset of LLC codes, and adjacent subsets are overlapped so that more spatial information can be captured. Additionally, HTM cortical learning algorithms have two processes: learning phase which make the HTM cell only receive most frequent LLC codes, and inhibition phase which ensure that the output of HTM regions is sparse. The experimental results on Caltech 101 and UIUC-Sport dataset show the improvement on the original LLC & SPM based model.

In this paper, a novel automatic DSM and remote sensing images registration scheme using template matching technique is developed. Due to the heterogeneity of DSM and remote sensing images, the emphases of our scheme are to describe the common feature between DSM and remote sensing images, and to generate a suitable template for template matching. Based on the sparse representation theory, we present a new feature descriptor, which can highlight the similarities of DSM and remote sensing images, and can be used to form a new kind of feature image. Meanwhile we present a criterion to choose the proper region from the feature image as the template which will ensure perfect template matching performance. The experiment results show that our scheme is efficient to fulfill the task of registration.

This paper firstly improves D.L.Plillips's representation about image restoration and then points out that image restoration is just a 'partial ill-posed' problem rather than a 'total ill-posed' problem---amplitude restoration is ill-posed but phase restoration is well-posed. Basing on the viewpoints, the paper proposes a restoration method, which cuts down phase-pollution caused by traditional regularization methods, that amplitude restoration is realized by regularization and phase restoration is achieved by algebraic method. Experimental results indicate that the proposed method performs well. It can efficiently restore image phase and elaborately preserve image details.

Due to the infection by heat transfer at the junction between different materials, edges in infrared(IR) images are usually blurred. The phenomenon named the edge effect almost always ignored by the existing methods for infrared images simulation. In this paper, we develop a simulation algorithm based on heat transfer model to obtain more perfect simulation results for infrared images. Meanwhile, to further enhance the fidelity of simulated IR images, a novel scheme to generate IR texture is presented. The experiment results show that our method can yield higher fidelity IR image than the existing simulation method.