The typical probability based point pattern matching method is coherent point drift (CPD) algorithm, which treats one point set as centroids of a Gaussian mixture model, and then fits it to the other. It uses the expectation maximization framework, where the point correspondences and transformation parameters are updated alternately. However, the anti-outlier performance of CPD is not robust enough as outliers have always been involved in the operation until the CPD converges. Hence, an automatic outlier suppression (AOS) mechanism is proposed. First, outliers are judged by a matching probability matrix. Then, transformation parameters are fitted using accurate matching point sets. Finally, the Gaussian centroids are forced to move coherently by this transformation model. AOS-CPD can efficiently improve the anti-outlier performance of rigid CPD. Furthermore, CPD is applied to image matching. A new local changing information descriptor-relative phase histogram (RPH) is designed and RPH-AOS-CPD is proposed to embed RPH measurement into AOS-CPD as a constraint condition. RPH-AOS-CPD makes full use of grayscale information besides having an excellent anti-outlier performance. The experimental results based on both synthetic and real data indicate that compared with other algorithms, AOS-CPD is more robust to outliers and RPH-AOS-CPD offers a good practicability and accuracy in image matching applications.
Laser detection based on the “cat’s eye effect” has become the hot research project for its initiative compared to the passivity of sound detection and infrared detection. And the target detection is one of the core technologies in this system. The paper puts forward a method for detecting small targets based on cumulative weighted value of target properties using given data. Firstly, we make a frame difference to the images, then make image processing based on Morphology Principles. Secondly, we segment images, and screen the targets; then find some interesting locations. Finally, comparing to a quantity of frames, we locate the target. We did an exam to 394 true frames, the experimental result shows that the mathod can detect small targets efficiently.
High-resolution, multi-pixels and large field of view (FOV) infrared (IR) detector is an important research direction, which greatly improves the target detection capability. This paper addresses the infrared target detection under the
guidance of attention mechanism. The Gabor filter is used to extract the elementary visual feature of infrared image for its
orientation selectiveness. Then it researches the reasons that produce visual saliency in frequency domain, and provides the
multichannel feature combination strategy to generate the feature map. Further, a novel saliency detection model using Fourier spectrum filtering, is presented to calculate feature regions of infrared image. Experimental results using a wide range of real IR images demonstrate that the proposed algorithm is robust and effective, yielding satisfying results for infrared target detection in large FOV with complex background and low SNR.
In order to implement real-time detection of hedgehopping target in large view-field infrared (LVIR) image, the
paper proposes a fast algorithm flow to extract the target region of interest (ROI). The ground building region was
rejected quickly and target ROI was segmented roughly through the background classification. Then the background
image containing target ROI was matched with previous frame based on a mean removal normalized product correlation
(MRNPC) similarity measure function. Finally, the target motion area was extracted by inter-frame difference in time
domain. According to the proposed algorithm flow, this paper designs the high-speed real-time signal processing
hardware platform based on FPGA + DSP, and also presents a new parallel processing strategy that called function-level
and task-level, which could parallel process LVIR image by multi-core and multi-task. Experimental results show that
the algorithm can extract low altitude aero target with complex background in large view effectively, and the new design
hardware platform could implement real time processing of the IR image with 50000x288 pixels per second in large
view-field infrared search system (LVIRSS).
With regard to target detection in complex background in high resolution image sequences attained by Wide Field of View Infrared Surveillance System, a rough-to-meticulous real-time target detection algorithm is proposed. In the rough detection phase, it attains initial high rate target detection by background matching and frame difference algorithm, based on the gray high frequency and moving characteristics of the target in the wide field of view image. In the meticulous recognition phase, focusing on the detected suspected target sliced images, it has further delicate recognition on the basis of targets’ characteristics to exclude those false jamming. The detection result of the test images shows, the algorithm enables stable detection with low-rate false alarm for distant dim targets, and has been applied to the signal processing of the Wide Field of View Infrared Surveillance System.
Conventional methods often assume that water region is homogeneous and bridge is brighter than background. They usually recognize target by parallel lines detection. But grayscale of bridge has bipolar problem in FLIR images due to interference of complex background and constraints of imaging conditions, which means that it can be greater or lower than river. Furthermore, water is not a homogeneous area as a whole because of the interference of water clutter and shoals. This paper proposes a novel algorithm of bridge recognition based on Gabor filter. Firstly, we obtain target ROI by extracting the horizontal line. And then ROI sub-images are enhanced by Gabor filter and target polarity is determined by bridge body detection. Finally, bridge recognition can be achieved by pier detection according to the target polarity and location of bridge body. Experimental results of nearly 3000 frames show that the proposed algorithm can effectively overcome problems such as bipolar target and low image contrast. It offers a good practicability and accuracy in bridge recognition in FLIR images.
An approach to infrared ship detection based on sea-sky-line(SSL) detection, ROI extraction and feature recognition is proposed in this paper. Firstly, considering that far ships are expected to be adjacent to the SSL, SSL is detected to find potential target areas. Radon transform is performed on gradient image to choose candidate SSLs, and detection result is given by fuzzy synthetic evaluation values. Secondly, in view of recognizable condition that there should be enough differences between target and background in infrared image, two gradient masks have been created and improved as practical guidelines in eliminating false alarm. Thirdly, extract ROI near the SSL by using multi-grade segmentation and fusion method after image sharpening, and unsuitable candidates are screened out according to the gradient masks and ROI shape. Finally, we segment the rest of ROIs by two-stage modified OTSU, and calculate target confidence as a standard measuring the facticity of target. Compared with other ship detection methods, proposed method is suitable for bipolar targets, which offers a good practicability and accuracy, and achieves a satisfying detection speed. Detection experiments with 200 thousand frames show that the proposed method is widely applicable, powerful in resistance to interferences and noises with a detection rate of above 95%, which satisfies the engineering needs commendably.
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.