Anticipating pedestrian crossing behavior in urban scenarios is a challenging task for autonomous vehicles. Early this year, a benchmark comprising JAAD and PIE datasets have been released. In the benchmark, several state-of-the-art methods have been ranked. However, most of the ranked temporal models rely on recurrent architectures. In our case, we propose, as far as we are concerned, the first self-attention alternative, based on transformer architecture, which has had enormous success in natural language processing (NLP) and recently in computer vision. Our architecture is composed of various branches which fuse video and kinematic data. The video branch is based on two possible architectures: RubiksNet and TimeSformer. The kinematic branch is based on different configurations of transformer encoder. Several experiments have been performed mainly focusing on pre-processing input data, highlighting problems with two kinematic data sources: pose keypoints and ego-vehicle speed. Our proposed model results are comparable to PCPA, the best performing model in the benchmark reaching an F1 Score of nearly $0.78$ against $0.77$. Furthermore, by using only bounding box coordinates and image data, our model surpasses PCPA by a larger margin ($F1=0.75$ vs. $F1=0.72$). Our model has proven to be a valid alternative to recurrent architectures, providing advantages such as parallelization and whole sequence processing, learning relationships between samples not possible with recurrent architectures.

Global localization is an important and widely studied problem for many robotic applications. Place recognition approaches can be exploited to solve this task, e.g., in the autonomous driving field. While most vision-based approaches match an image w.r.t. an image database, global visual localization within LiDAR-maps remains fairly unexplored, even though the path toward high definition 3D maps, produced mainly from LiDARs, is clear. In this work we leverage Deep Neural Network (DNN) approaches to create a shared embedding space between images and LiDAR-maps, allowing for image to 3D-LiDAR place recognition. We trained a 2D and a 3D DNN that create embeddings, respectively from images and from point clouds, that are close to each other whether they refer to the same place. An extensive experimental activity is presented to assess the effectiveness of the approach w.r.t. different learning paradigms, network architectures, and loss functions. All the evaluations have been performed using the Oxford Robotcar Dataset, which encompasses a wide range of weather and light conditions.

In this paper, we present a novel probabilistic technique, based on the Bayes filter, able to estimate the user location, even with unreliable sensor data coming only from fixed sensors in the monitored environment. Our approach has been extensively tested in a home-like environment, as well as in a real home, and achieves very good results. We present results on two datasets, representative of real life conditions, collected during the testing phase. We detect the patient location with subroom accuracy, an improvement over the state of the art for localization using only environmental sensors. The main drawback is that it is only suitable for applications where a single person is present in the environment, like as with other approaches that do not use any mobile device. For this reason, we introduced the “telehomecare” term, therefore differentiating from generic telemedicine applications, where many people can be in the same environment at the same time.