Sohyun Kim

Robust Ground Target Detection by SAR and IR Sensor Fusion Using Adaboost-Based Feature Selection

Long-range ground targets are difficult to detect in a noisy cluttered environment using either synthetic aperture radar (SAR) images or infrared (IR) images. SAR-based detectors can provide a high detection rate with a high false alarm rate to background scatter noise. IR-based approaches can detect hot targets but are affected strongly by the weather conditions. This paper proposes a novel target detection method by decision-level SAR and IR fusion using an Adaboost-based machine learning scheme to achieve a high detection rate and low false alarm rate. The proposed method consists of individual detection, registration, and fusion architecture. This paper presents a single framework of a SAR and IR target detection method using modified Boolean map visual theory (modBMVT) and feature-selection based fusion. Previous methods applied different algorithms to detect SAR and IR targets because of the different physical image characteristics. One method that is optimized for IR target detection produces unsuccessful results in SAR target detection. This study examined the image characteristics and proposed a unified SAR and IR target detection method by inserting a median local average filter (MLAF, pre-filter) and an asymmetric morphological closing filter (AMCF, post-filter) into the BMVT. The original BMVT was optimized to detect small infrared targets. The proposed modBMVT can remove the thermal and scatter noise by the MLAF and detect extended targets by attaching the AMCF after the BMVT. Heterogeneous SAR and IR images were registered automatically using the proposed RANdom SAmple Region Consensus (RANSARC)-based homography optimization after a brute-force correspondence search using the detected target centers and regions. The final targets were detected by feature-selection based sensor fusion using Adaboost. The proposed method showed good SAR and IR target detection performance through feature selection-based decision fusion on a synthetic database generated by OKTAL-SE.

Infrared small target discrimination using sequential forward feature selection with AUC mettric

Infrared search and track (IRST) is an important research topic in military applications in surveillance and precise guided missiles. The bottleneck of IRST algorithm is huge number of false alarms in real world applications due to sky cloud, sea-glints, and ground clutters. This paper presents a novel target discrimination method using forward feature selection with area under ROC curve (AUC) metric. Experimental results on real target sequences validate the feasibility of the proposed method.

Synthetic SAR/IR database generation for sensor fusion-based A.T.R.

Recently, the sensor fusion research has been in progress for effective ground target detection. SAR and IR sensors are complementary because the IR sensor has a high resolution, SAR sensor is not effected by the weather. In research, The DB of the SAR/IR sensor is essential. But database(DB) of the SAR/IR sensor dose not exist or is not released. It is also difficult to acquire the DB directly because of cost and environmental issues. Therefore, this paper proposed a method to build the DB with synthetic image generation simulator OKTAL-SE. We generate day and night images, and compare the features.

Regularization approach to scene-based nonuniformity correction

Abstract. Various scene-based nonuniformity correction (SBNUC) methods have been proposed to diminish the residual nonuniformity (RNU) of the infrared focal plane array (IRFPA) sensors. Most existing SBNUC techniques require a relatively large number of image frames to reduce the RNU. In some applications, however, there is not enough time for capturing a large number of image frames prior to the camera operation, or only several image frames are available to users. A new scene-based approach that can correct the RNU using only several image frames is proposed. The proposed method formulates the SBNUC process as an energy minimization problem. In the proposed energy function, we introduce regularization terms for the parameter regarding the responsivity of the IRFPA as well as for the true scene irradiance. Correction results are obtained by minimizing the energy function using a numerical technique. Experimental results demonstrate the effectiveness of the proposed method.

Double Weight-Based SAR and Infrared Sensor Fusion for Automatic Ground Target Recognition with Deep Learning

This paper presents a novel double weight-based synthetic aperture radar (SAR) and infrared (IR) sensor fusion method (DW-SIF) for automatic ground target recognition (ATR). IR-based ATR can provide accurate recognition because of its high image resolution but it is affected by the weather conditions. On the other hand, SAR-based ATR shows a low recognition rate due to the noisy low resolution but can provide consistent performance regardless of the weather conditions. The fusion of an active sensor (SAR) and a passive sensor (IR) can lead to upgraded performance. This paper proposes a doubly weighted neural network fusion scheme at the decision level. The first weight ( α ) can measure the offline sensor confidence per target category based on the classification rate for an evaluation set. The second weight ( β ) can measure the online sensor reliability based on the score distribution for a test target image. The LeNet architecture-based deep convolution network (14 layers) is used as an individual classifier. Doubly weighted sensor scores are fused by two types of fusion schemes, such as the sum-based linear fusion scheme ( α β -sum) and neural network-based nonlinear fusion scheme ( α β -NN). The experimental results confirmed the proposed linear fusion method ( α β -sum) to have the best performance among the linear fusion schemes available (SAR-CNN, IR-CNN, α -sum, β -sum, α β -sum, and Bayesian fusion). In addition, the proposed nonlinear fusion method ( α β -NN) showed superior target recognition performance to linear fusion on the OKTAL-SE-based synthetic database.

Computationally Efficient Automatic Coast Mode Target Tracking Based on Occlusion Awareness in Infrared Images

This paper proposes the automatic coast mode tracking of centroid trackers for infrared images to overcome the target occlusion status. The centroid tracking method, using only the brightness information of an image, is still widely used in infrared imaging tracking systems because it is difficult to extract meaningful features from infrared images. However, centroid trackers are likely to lose the track because they are highly vulnerable to screened status by the clutter or background. Coast mode, one of the tracking modes, maintains the servo slew rate with the tracking rate right before the loss of track. The proposed automatic coast mode tracking method makes decisions regarding entering coast mode by the prediction of target occlusion and tries to re-lock the target and resume the tracking after blind time. This algorithm comprises three steps. The first step is the prediction process of the occlusion by checking both matters which have target-likelihood brightness and which may screen the target despite different brightness. The second step is the process making inertial tracking commands to the servo. The last step is the process of re-locking a target based on the target modeling of histogram ratio. The effectiveness of the proposed algorithm is addressed by presenting experimental results based on computer simulation with various test imagery sequences compared to published tracking algorithms. The proposed algorithm is tested under a real environment with a naval electro-optical tracking system (EOTS) and airborne EO/IR system.

Infrared Variation Optimized Deep Convolutional Neural Network for Robust Automatic Ground Target Recognition

Automatic infrared target recognition (ATR) is a traditionally unsolved problem in military applications because of the wide range of infrared (IR) image variations and limited number of training images, which is caused by various 3D target poses, non-cooperative weather conditions, and difficult target acquisition environments. Recently, deep convolutional neural network-based approaches in RGB images (RGB-CNN) showed breakthrough performance in computer vision problems, such as object detection and classification. The direct use of the RGB-CNN to IR ATR problem fails to work because of the IR database problems. This paper presents a novel infrared variation-optimized deep convolutional neural network (IVO-CNN) by considering database management, such as increasing the database by a thermal simulator, controlling the image contrast automatically and suppressing the thermal noise to reduce the effects of infrared image variations in deep convolutional neural network-based automatic ground target recognition. The experimental results on the synthesized infrared images generated by the thermal simulator (OKTAL-SE) validated the feasibility of IVO-CNN for military ATR applications.

Covariance-based band selection and its application to near-real-time hyperspectral target detection

Abstract. The matched filter (MF) and adaptive coherence estimator (ACE) show great effectiveness in hyperspectral target detection applications. Practical applications in which on-board processing is generally required demand real-time or near-real-time implementation of these detectors. However, a vast amount of hyperspectral data may make real-time or near-real-time implementation of the detection algorithms almost impossible. Band selection can be one of the solutions to this problem by reducing the number of spectral bands. We propose a new band selection method that prioritizes spectral bands based on their influence on the detection performance of the MF and ACE and discards the least influential bands. We validate the performance of our method using real hyperspectral images. We also demonstrate our technique on near-real-time detection tasks and show it to be a feasible approach to the tasks.

Target size prediction and verification by geometrical analysis and SE-WORKBENCH for ground target detection

Conventional target detectors use filter kernel to enhance target signature and depress background clutter. It is important to use a predefined kernel size to enhance target detection performance and speed. This paper presents a geometrical analysis of ground target size using a set of target acquisition parameters and verifies predicted the target size by comparing with the output of commercial simulator (OKTAL SE-WORKBENCH).

Variation analysis of 24 hour winter infrared images for small target detection

This paper reports the results of variation analysis of infrared images acquired using a long wave infrared camera over a 24 hour period. The analysis was conducted in terms of the small infrared target detection parameters, such as the average background intensity, contrast between the target signal and average background intensity, standard deviation of the background, and the signal-to-clutter ratio for various backgrounds, such as remote mountains, buildings, near field and sky. The detection parameters were compared according to the recording time, temperature and humidity. Through variation analysis, the optimal target detection conditions could be obtained or the detection threshold could be controlled to maximize the detection performance.