As an important application of computer vision, visual tracking has being a fundamental topic. Compared with visible image, infrared image has the characteristic of low resolution, blurred contour and single color feature. Thus, it is still a challenge for infrared object tracking. Further, it is difficult to balance the real-time performance and accuracy. This paper proposed a tracker based on the SiamRPN tracker with a deeper and lightweight MobileNet V2 structure as the backbone network. During network training, the weights are updated by the scheme of the model-independent metalearning method. The computed model only passes a few gradient descents on the first frame can obtains the most suitable for the current frame. In the end, the tracker is tested on various datasets. Experimental results show that the tracker can achieve a balance between tracking accuracy and inference speed, which is crucial for deployment on mobile devices.
Compared with traditional Lidar, photon counting laser radar uses a high repetition rate and low pulse energy detection mechanism. The efficiency of laser echo can be improved by more than two orders of magnitude compared with traditional Lidar systems benefitting from the use of extremely sensitive Gm-APD (Geiger mode avalanche photodiode), which greatly improves the detection probability of the system. However, it becomes difficult to detect fast-moving targets within a long counting time, especially under the interference of high background noise. In order to detect high background, long distance and fast moving targets, we propose a dynamic TCSPC method based on point-line duality. The proposed method clusters the point clouds with a certain relationship in the original point cloud space, and finds the corresponding points in the parameter space that can connect some point clouds in a certain analytical form. Simulation results show that highspeed moving target can be detected.
In this paper, a far-field pseudo-thermal correlation imaging system is proposed which is mainly composed of laser, thermal field modulation system, speckle far field emission system and high-sensitivity intensity fluctuation detection system, etc.. Because the correlation imaging system is based on the principle of intensity fluctuation statistical measurement, it needs to be reconstructed after multiple measurements. An image reconstruction algorithm based on compressive sensing is applied in this paper, which makes full use of sparsity constraints to effectively improve the image restoration effect. Finally, the feasibility of the method is verified by actual imaging test. The experimental results show that the proposed system can clearly image the remote target and obtain better recovery images under the same sampling times.
A division of aperture medium wave infrared Stokes imaging polarimeter (ISIP) with optimal linear polarization measurements is presented. The focal plane array of the ISIP is divided into four independent imaging channels by a lens array, which is turned into four independent polarimetric analyzing channels by placing four linear polarizers of different orientation angles in front of each channel and a wave plate in one of the channels. The experiments are performed for detecting camouflaged targets by using the optimized ISIP, which demonstrate that the polarimetric images are effective in detecting camouflaged targets form natural background and improving the signal to noise ratio of target images.
The Hyperspectral infrared imaging technique is an optical detection technology which integrates spectral measurement technology and infrared imaging technology. It can not only obtain the spectral information of the target, but also obtain the image information, which provides a powerful guarantee for the accurate recognition of the target. Due to the spectral characteristics of the mid-wave infrared, mid-infrared hyperspectral imaging system is widely used in civilian and military areas, such as geographical remote sensing, target detection and thermal fluent analysis. With the development of related technologies, imaging spectroscopy technology has diversified. In this paper, the push-type mid-wave infrared reflection planar grating hyperspectral imaging system is selected as the design target. The system consists of: front optical system, slit, collimation system, grating spectroscopic system, imaging optical system, imaging electrical component and control module.
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.