Automatic Detection Of Small Targets Research Articles

Automatic detection method of small target in tennis game video based on deep learning

Due to the large number of frames and low video resolution, tennis match videos cannot accurately identify and extract effective data, which reduces the level of fine analysis of tennis matches. In order to solve the problem of poor detection effect of small targets in tennis video, an automatic detection method of small targets in tennis video based on deep learning is proposed. Non-maximum suppression algorithm is used to determine the position of the target between different adjacent video image sequences, and SVM classifier is used to train a large number of target behaviors. According to the hierarchical structure of dataset annotation, the hierarchical structure of tennis video for deep learning is optimized. The reconstruction algorithm is used to enhance the video image in the input VOC data set and improve the fine segmentation effect of the image. The difference video image is binarized to complete the automatic detection of small targets in tennis video. The experimental results show that the proposed method has high integrity of tennis video information collection, high recognition accuracy and short detection time.

Automatic detection of sea-sky horizon line and small targets in maritime infrared imagery

It is usually difficult but important to extract distant targets from sea clutters and clouds since the targets are small compared to the pixel field of view. In this paper, an algorithm based on wavelet transformation is proposed for automatic detection of small targets under the maritime background. We recognize that the distant small targets generally appear near the sea-sky horizon line and noises lie along the direction of sea-sky horizon line. So the sea-sky horizon is located firstly by examining the approximate image of a Haar wavelet decomposition of the original image. And the equation of the sea-sky horizon is set up, no matter whether the sea-sky horizon is horizontal or not. Since the sea-sky horizon is located, not only the potential area but also the strip direction of noise is got. Then the modified mutual wavelet energy combination algorithm is applied to extract targets with targets being marked by red windows. Computer simulations are shown to validate the great adaptability of the sea-sky horizon line detection and the accuracy of the small targets detection. The algorithm should be useful to engineers and scientists to design precise guidance or maritime monitoring system.

A novel spatial–temporal detection method of dim infrared moving small target

Moving small target detection under complex background in infrared image sequence is one of the major challenges of modern military in Early Warning Systems (EWS) and the use of Long-Range Strike (LRS). However, because of the low SNR and undulating background, the infrared moving small target detection is a difficult problem in a long time. To solve this problem, a novel spatial–temporal detection method based on bi-dimensional empirical mode decomposition (EMD) and time-domain difference is proposed in this paper. This method is downright self-data decomposition and do not rely on any transition kernel function, so it has a strong adaptive capacity. Firstly, we generalized the 1D EMD algorithm to the 2D case. In this process, the project has solved serial issues in 2D EMD, such as large amount of data operations, define and identify extrema in 2D case, and two-dimensional signal boundary corrosion. The EMD algorithm studied in this project can be well adapted to the automatic detection of small targets under low SNR and complex background. Secondly, considering the characteristics of moving target, we proposed an improved filtering method based on three-frame difference on basis of the original difference filtering in time-domain, which greatly improves the ability of anti-jamming algorithm. Finally, we proposed a new time–space fusion method based on a combined processing of 2D EMD and improved time-domain differential filtering. And, experimental results show that this method works well in infrared small moving target detection under low SNR and complex background.

Automatic Detection of Targets Using Center-Surround Difference and Local Thresholding

This paper proposes a new target detection method in low contrast forward looking infrared (FLIR) images. Automatic detection of small targets in remotely sensed images is a difficult and challenging work. The goal is to find out target locations with low false alarms in a thermal infrared scene of battlefield. The interesting targets are military vehicles such as battle tanks and armored personal carriers in ground-to-ground scenarios. The proposed method consists of three following stages. First, center-surround difference is proposed in order to find salient areas in an input image. Second, local thresholding for a region of interest (ROI) is proposed. The ROI is selected on the basis of a salient region that is the result of first step. Third, the shape of extracted binary images is compared with binary target templates using size and affinity to remove clutters. In the experiments, the proposed method is compared with morphology method using many natural infrared images with high variability. The result demonstrates that our method is superior to the morphological method in terms of receiver operating characteristic (ROC) curve and average computation time.

Automatic detection of small objects from their infrared state-of-polarization vectors.

A technique for automatic detection of targets from their infrared signature's state-of-polarization vector is described. The bounds on the Bayesian total probability of errors are estimated from the observed Stokes vector imagery and used as metrics for separating targets from background clutter. The performance of the proposed approach for objects under various geometries is studied in terms of receiver operating characteristic curves. The new results, which have been obtained from data from the U.S. Air Force's Infrared Modeling and Analysis polarimetric infrared simulation tool, indicate the usefulness of polarimetric infrared signatures for the automatic detection of small targets.