Ship detection in high-resolution synthetic aperture radar (SAR) imagery is a challenging problem in the case of complex environments, especially inshore and offshore scenes. Nowadays, the existing methods of SAR ship detection mainly use low-resolution representations obtained by classification networks or recover high-resolution representations from low-resolution representations in SAR images. As the representation learning is characterized by low resolution and the huge loss of resolution makes it difficult to obtain accurate prediction results in spatial accuracy; therefore, these networks are not suitable to ship detection of region-level. In this paper, a novel ship detection method based on a high-resolution ship detection network (HR-SDNet) for high-resolution SAR imagery is proposed. The HR-SDNet adopts a novel high-resolution feature pyramid network (HRFPN) to take full advantage of the feature maps of high-resolution and low-resolution convolutions for SAR image ship detection. In this scheme, the HRFPN connects high-to-low resolution subnetworks in parallel and can maintain high resolution. Next, the Soft Non-Maximum Suppression (Soft-NMS) is used to improve the performance of the NMS, thereby improving the detection performance of the dense ships. Then, we introduce the Microsoft Common Objects in Context (COCO) evaluation metrics, which provides not only the higher quality evaluation metrics average precision (AP) for more accurate bounding box regression, but also the evaluation metrics for small, medium and large targets, so as to precisely evaluate the detection performance of our method. Finally, the experimental results on the SAR ship detection dataset (SSDD) and TerraSAR-X high-resolution images reveal that (1) our approach based on the HRFPN has superior detection performance for both inshore and offshore scenes of the high-resolution SAR imagery, which achieves nearly 4.3% performance gains compared to feature pyramid network (FPN) in inshore scenes, thus proving its effectiveness; (2) compared with the existing algorithms, our approach is more accurate and robust for ship detection of high-resolution SAR imagery, especially inshore and offshore scenes; (3) with the Soft-NMS algorithm, our network performs better, which achieves nearly 1% performance gains in terms of AP; (4) the COCO evaluation metrics are effective for SAR image ship detection; (5) the displayed thresholds within a certain range have a significant impact on the robustness of ship detectors.

No abstract

This paper presents a methodology for using vehicle trajectory data to study the intradriver heterogeneity of driving behavior between the acceleration process and the deceleration process. Trajectory data were collected during peak hours on Dutch Motorway A2. Criteria were proposed for the selection of subtrajectories corresponding to both the acceleration and the deceleration processes of car-following. With the application of these subtrajectories to calibrate three types of models (the Helly model, the Gipps model, and the intelligent driver model), it was found that obvious intradriver heterogeneities existed in driving behaviors between the acceleration and deceleration processes of car-following: (a) the average response time of drivers in the acceleration process was longer than that in the deceleration process according to the prediction of the Helly and intelligent driver models; (b) drivers were apt to respond more intensively to surrounding traffic in the deceleration process than they did in the acceleration process; and (c) more than 65% of drivers involved in this study drove in obviously different styles between the acceleration and deceleration processes. Moreover, a compensation for the response delay from model parameters was observed, and all three models presented low robustness in predicting driving behaviors of one car-following process with the parameters optimized from the data of other car-following processes. This work not only provides insight into intradriver heterogeneity in car-following behaviors but also suggests some important criteria for car-following modeling.

No abstract

No abstract

No abstract

No abstract

No abstract