Due to the flexible configuration and maneuvering platform, bistatic synthetic aperture radar (SAR) plays an important role in modern remote sensing applications, but the non-ideal track simultaneously introduces model mismatch and spatial-variant phase problems. This paper proposes a sub-aperture parametric polar format algorithm (PFA) for high-resolution bistatic spotlight SAR imaging. First, a bistatic parametric polar format algorithm is proposed to focus on the generally configured bistatic SAR data. A high-precision range model in the bistatic range and ellipsoid parameter angle coordinate space is established to modify the PFA interpolation kernels. To further enhance the azimuth resolution, the PFA sub-images are fused in the image domain based on the coordinate transformation between the unified Cartesian coordinates and local imaging polar coordinates. During the sub-image fusion, in order to ensure the accurate projection and non-aliasing spectrum, we also consider the geometric deformation of the coarse PFA image and analyze the wavenumber support region along with the Nyquist sampling requirement. This novel sub-aperture method, which is theoretically more efficient than the fast back-projection algorithm, alleviates the limitation of full aperture resolution on PFA’s depth of focus. Finally, our method is applied to the general bistatic spotlight SAR data, involving the level-flight airborne transmitter and the dive hypersonic vehicle-borne receiver, and the results of both points and distributed targets demonstrate its effectiveness and efficiency.

We present a novel Neural Embedding Spatio-Temporal (NEST) point process model for spatio-temporal discrete event data and develop an efficient imitation learning (a type of reinforcement learning) based approach for model fitting. Despite the rapid development of one-dimensional temporal point processes for discrete event data, the study of spatial-temporal aspects of such data is relatively scarce. Our model captures complex spatio-temporal dependence between discrete events by carefully design a mixture of heterogeneous Gaussian diffusion kernels, whose parameters are parameterized by neural networks. This new kernel is the key that our model can capture intricate spatial dependence patterns and yet still lead to interpretable results as we examine maps of Gaussian diffusion kernel parameters. The imitation learning model fitting for the NEST is more robust than the maximum likelihood estimate. It directly measures the divergence between the empirical distributions between the training data and the model-generated data. Moreover, our imitation learning-based approach enjoys computational efficiency due to the explicit characterization of the reward function related to the likelihood function; furthermore, the likelihood function under our model enjoys tractable expression due to Gaussian kernel parameterization. Experiments based on real data show our method’s good performance relative to the state-of-the-art and the good interpretability of NEST’s result.

This study proposes a clutter suppression approach and the corresponding ground moving target imaging algorithm for hypersonic vehicle (HSV) borne synthetic aperture radar (SAR) system with multiple‐input–multiple‐output (MIMO) antenna. HSV‐borne radar platforms fly with a high speed, which can lead to severe Doppler ambiguity, and the radar system usually cannot provide enough channel freedom degree for clutter suppression. In this study, an SAR ground moving target indication (GMTI) approach with MIMO antenna is presented for HSV‐borne radar. Compared with the traditional multichannel SAR GMTI methods, the proposed approach can provide more space freedom degree and obtain a wider imaging swath without decreasing pulse repetition frequency. Besides, the improved deramp space‐time adaptive processing method decreases the ambiguity times of the ground clutter and focuses the moving target. The simulation results validate the effectiveness of the proposed method.

In general image recognition problems, discriminative information often lies in local image patches. For example, most human identity information exists in the image patches containing human faces. The same situation stays in medical images as well. "Bodypart identity" of a transversal slice-which bodypart the slice comes from-is often indicated by local image information, e.g., a cardiac slice and an aorta arch slice are only differentiated by the mediastinum region. In this work, we design a multi-stage deep learning framework for image classification and apply it on bodypart recognition. Specifically, the proposed framework aims at: 1) discover the local regions that are discriminative and non-informative to the image classification problem, and 2) learn a image-level classifier based on these local regions. We achieve these two tasks by the two stages of learning scheme, respectively. In the pre-train stage, a convolutional neural network (CNN) is learned in a multi-instance learning fashion to extract the most discriminative and and non-informative local patches from the training slices. In the boosting stage, the pre-learned CNN is further boosted by these local patches for image classification. The CNN learned by exploiting the discriminative local appearances becomes more accurate than those learned from global image context. The key hallmark of our method is that it automatically discovers the discriminative and non-informative local patches through multi-instance deep learning. Thus, no manual annotation is required. Our method is validated on a synthetic dataset and a large scale CT dataset. It achieves better performances than state-of-the-art approaches, including the standard deep CNN.

In this paper, a novel public key encryption scheme for large image is presented based on elliptic curve. As a public key encryption scheme, it does not need to exchange and distribute secret keys. Based on elliptic curve discrete logarithm problem (ECDLP), the scheme has high security. The simulation results show that the presented scheme is computationally less complex than ECC (Elliptic Curve Cryptography) and suitable for large image encryption.

In this paper, we propose a learning-based algorithm for automatic medical image annotation based on robust aggregation of learned local appearance cues, achieving high accuracy and robustness against severe diseases, imaging artifacts, occlusion, or missing data. The algorithm starts with a number of landmark detectors to collect local appearance cues throughout the image, which are subsequently verified by a group of learned sparse spatial configuration models. In most cases, a decision could already be made at this stage by simply aggregating the verified detections. For the remaining cases, an additional global appearance filtering step is employed to provide complementary information to make the final decision. This approach is evaluated on a large-scale chest radiograph view identification task, demonstrating a very high accuracy ( > 99.9%) for a posteroanterior/anteroposterior (PA-AP) and lateral view position identification task, compared with the recently reported large-scale result of only 98.2% (Luo, , 2006). Our approach also achieved the best accuracies for a three-class and a multiclass radiograph annotation task, when compared with other state of the art algorithms. Our algorithm was used to enhance advanced image visualization workflows by enabling content-sensitive hanging-protocols and auto-invocation of a computer aided detection algorithm for identified PA-AP chest images. Finally, we show that the same methodology could be utilized for several image parsing applications including anatomy/organ region of interest prediction and optimized image visualization.

Automatic coronary artery centerline extraction from 3D CT Angiography (CTA) has significant clinical importance for diagnosis of atherosclerotic heart disease. The focus of past literature is dominated by segmenting the complete coronary artery system as trees by computer. Though the labeling of different vessel branches (defined by their medical semantics) is much needed clinically, this task has been performed manually. In this paper, we propose a hierarchical machine learning approach to tackle the problem of tubular structure parsing in medical imaging. It has a progressive three-tiered classification process at volumetric voxel level, vessel segment level, and inter-segment level. Generative models are employed to project from low-level, ambiguous data to class-conditional probabilities; and discriminative classifiers are trained on the upper-level structural patterns of probabilities to label and parse the vessel segments. Our method is validated by experiments of detecting and segmenting clinically defined coronary arteries, from the initial noisy vessel segment networks generated by low-level heuristics-based tracing algorithms. The proposed framework is also generically applicable to other tubular structure parsing tasks.

We present a novel method to effectively segment the three dimensional MR brain images (volumes) with severe intensity nonuniformity. The segmentation problem was formulated using maximum a posterior probability and Markov random filed (MAP-MRF) framework. A novel spatial Gaussian mixture model (SGMM) is used to represent the intensity probability distribution of each of the three brain tissues (WM, GM and CSF), and MRF is used to compute the prior probability. This method consists of a learning process based on expectation maximization algorithm (EM) to estimate the parameters of SGMM, and a classification algorithm based on iterated conditional modes (ICM) to perform the segmentation of the sequential brain images using the parameters obtained from the learning process. The results on the simulated and twenty in vivo MR brain volumes demonstrate the efficiency of this method. We also present the comparison results with other published methods.