Super-cavitation morphological parameter information of the cross-media projectile reflects high-speed projectiles motion characteristics. Accurate measurement of super-cavitation morphological parameters is the basis for high-speed projectile structural design and optimization, becoming a research hotspot of the underwater ballistic testing field. With the development of the high-speed photography technology, recording the evolution process of projectile cavitation morphologies by high-speed cameras and acquiring super-cavitation morphological information through image processing methods have become one of the main research directions. Aiming at reducing the large workload of manual interpretation from super-cavitation images, a multi-scale space-based automatic contour extraction algorithm for super cavitation images captured by the array cross-media high-speed imaging system is introduced in this paper. The Canny edge detection method is applied to obtain the binary edge image with coarse extraction super-cavitation edge after image pre-processing. The super-cavitation contour point set is searched in the binary edge image and small gaps between adjacent endpoints are filled at the same time. The contour extraction algorithm based on the multi-space curvature characteristics is presented to calculate the curvature value of each contour point in the high-scale space, and the curvature feature points are determined by the threshold judgment approach. The contour feature points extracted in the high-scale space are located in the low-scale space precisely, and the super-cavitation contour is extracted. Experimental results show that, the proposed method can reduce the workload from manual interpretation while improve the accuracy of contour positioning, which can provide basic data support for the cross-media high-speed projectile super-cavitation morphological parameter measurement.
Robust infrared small target detection is of great essence for infrared search and track system. To detect the low signal-to-clutter ratio (SCR) target under the interference of high-intensity structural background, we propose an infrared small target detection method using multidirectional derivative and local contrast difference (MDLCD). Noting that infrared small target tends to have 2D Gaussian-like shape, we present a new multidirectional derivative model to reflect this distribution in each direction, which effectively enhances the target. Additionally, the adjacent background is applied to construct the local contrast difference model, whose role is to further suppress the high-intensity structural clutters. After this, the MDLCD map is obtained by weighting the above two filtered maps, along with an adaptive segmentation operation to finally extract the target. Experimental results verify that MDLCD achieves satisfactory performances in terms of SCR gain (SCRG) and background suppression factor (BSF).
Motion object tracking is one of the most important research directions in computer vision. Challenges in designing a robust tracking method are usually caused by partial or complete occlusions on targets. However, motion object tracking algorithm based on multiple cameras according to the homography relation in three views can deal with this issue effectively since the information combining from multiple cameras in different views can make the target more complete and accurate. In this paper, a robust visual tracking algorithm based on the homography relations of three cameras in different views is presented to cope with the occlusion. First of all, being the main contribution of this paper, the motion object tracking algorithm based on the low-rank matrix representation under the framework of the particle filter is applied to track the same target in the public region respectively in different views. The target model and the occlusion model are established and an alternating optimization algorithm is utilized to solve the proposed optimization formulation while tracking. Then, we confirm the plane in which the target has the largest occlusion weight to be the principal plane and calculate the homography to find out the mapping relations between different views. Finally, the images of the other two views are projected into the main plane. By making use of the homography relation between different views, the information of the occluded target can be obtained completely. The proposed algorithm has been examined throughout several challenging image sequences, and experiments show that it overcomes the failure of the motion tracking especially under the situation of the occlusion. Besides, the proposed algorithm improves the accuracy of the motion tracking comparing with other state-of-the-art algorithms.
In practical application scenarios like video surveillance and human-computer interaction, human body movements are uncertain because the human body is a non-rigid object. Based on the fact that the head-shoulder part of human body can be less affected by the movement, and will seldom be obscured by other objects, in human detection and recognition, a head-shoulder model with its stable characteristics can be applied as a detection feature to describe the human body. In order to extract the head-shoulder contour accurately, a head-shoulder model establish method with combination of edge detection and the mean-shift algorithm in image clustering has been proposed in this paper. First, an adaptive method of mixture Gaussian background update has been used to extract targets from the video sequence. Second, edge detection has been used to extract the contour of moving objects, and the mean-shift algorithm has been combined to cluster parts of target’s contour. Third, the head-shoulder model can be established, according to the width and height ratio of human head-shoulder combined with the projection histogram of the binary image, and the eigenvectors of the head-shoulder contour can be acquired. Finally, the relationship between head-shoulder contour eigenvectors and the moving objects will be formed by the training of back-propagation (BP) neural network classifier, and the human head-shoulder model can be clustered for human detection and recognition. Experiments have shown that the method combined with edge detection and mean-shift algorithm proposed in this paper can extract the complete head-shoulder contour, with low calculating complexity and high efficiency.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.