High-resolution automotive radars, which are widely used nowadays, yield multiple measurements per frame from a single target. Clustering these measurements accurately and finding the tight bounding boxes are two challenging problems. In this work, the shape is estimated using a rectangular bounding box using the position and range rate measurements from the radar. While the Doppler (or range rate) measurements provide extra information about the target velocity, the presence of micro-Doppler (for example, returns from tires of a car) can significantly degrade the clustering, bounding box and heading estimates. It is necessary to cluster the measurements corresponding to different targets, as well as those that occur due to micro-Doppler. A clustering method is developed that can effectively use the Doppler information to differentiate closely spaced targets while avoiding the drawbacks of microDoppler. The bounding box estimate is refined by using only the measurements corresponding to the target bulk and, in turn, further aids in clustering iteratively. The effectiveness of the proposed approach is verified using simulations for different scenarios.

This paper analyses the track-level detection of ghost tracks in multitarget tracking with a known reflection surface. In a real-world target tracking problem, the number of targets in surveillance is unknown to the platform. Thus, the tracker will be inadequate to distinguish the direct target return from the multipath return during the track initialization. Therefore, ghost tracks can be created with multipath measurements when they are considered direct path measurements. Even though the possible multipath measurement could be predicted for the existing tracks at a given instance, it is hard to decide whether the detected track is a multipath or a new target. Thus, a sequence of time instances needs to be considered to determine the track status. In this work, we propose a classification model to classify a track as either a multipath or direct path using an LSTM network with sequential data. Additionally, the performance of the proposed approach is compared with four other algorithms using a simulation-based dataset.

In the last five years, the state-of-the-art in computer vision has improved greatly thanks to an increased use of deep convolutional neural networks (CNNs), advances in graphical processing unit (GPU) acceleration and the availability of large labelled datasets such as ImageNet. Obtaining datasets as comprehensively labelled as ImageNet for ship classification remains a challenge. As a result, we experiment with pre-trained CNNs based on the Inception and ResNet architectures to perform ship classification. Instead of training a CNN using random parameter initialization, we use transfer learning. We fine-tune pre-trained CNNs to perform maritime vessel image classification on a limited ship image dataset. We achieve a significant improvement in classification accuracy compared to the previous state-of-the-art results for the Maritime Vessel (Marvel) dataset.