In Smart City and Vehicle-to-Everything (V2X) systems, acquiring pedestrians’ accurate locations is crucial to traffic and pedestrian safety. Current systems adopt cameras and wireless sensors to estimate people’s locations via sensor fusion. Standard fusion algorithms, however, become inapplicable when multi-modal data is not associated. For example, pedestrians are out of the camera field of view, or data from the camera modality is missing. To address this challenge and produce more accurate location estimations for pedestrians, we propose a localization solution based on a Generative Adversarial Network (GAN) architecture. During training, it learns the underlying linkage between pedestrians’ camera-phone data correspondences. During inference, it generates refined position estimations based only on pedestrians’ phone data that consists of GPS, IMU, and FTM. Results show that our GAN produces 3D coordinates at 1 to 2 meters localization error across 5 different outdoor scenes. We further show that the proposed model supports self-learning. The generated coordinates can be associated with pedestrians’ bounding box coordinates to obtain additional camera-phone data correspondences. This allows automatic data collection during inference. Results show that after fine-tuning the GAN model on the expanded dataset, localization accuracy is further improved by up to 26%.

Connected vehicles can benefit from sharing and merging their observations to develop a more complete understanding of the traffic scene and track traffic participants behind obstructions. Although vehicle-to-vehicle(V2V) communications provide a channel for point cloud data sharing, it is challenging to align point clouds from two vehicles with state-of-the-art techniques due to localization errors, visual obstructions, and differences in perspective. Therefore, we propose a two-phase point cloud registration mechanism to fuse point clouds which focuses on key objects in the scene where the point clouds are most similar and infer the transformation from those. Our system first identifies co-visible objects between vehicle views based on hyper-graph matching using multiple similarity metrics, and then refines the overlap region between co-visible objects across the views for point cloud registration. The system is evaluated based on both experimental and simulation data, which shows tremendous performance improvement when combing with state-of-art baselines.

Tracking subjects in videos is one of the most widely used functions in camera-based IoT applications such as security surveillance, smart city traffic safety enhancement, vehicle to pedestrian communication and so on. In computer vision domain, tracking is usually achieved by first detecting subjects, then associating detected bounding boxes across video frames. Typically, frames are transmitted to a remote site for processing, incurring high latency and network costs. To address this, we propose ViFiT, a transformer-based model that reconstructs vision bounding box trajectories from phone data (IMU and Fine Time Measurements). It leverages a transformer's ability of better modeling long-term time series data. ViFiT is evaluated on Vi-Fi Dataset, a large-scale multimodal dataset in 5 diverse real world scenes, including indoor and outdoor environments. Results demonstrate that ViFiT outperforms the state-of-the-art approach for cross-modal reconstruction in LSTM Encoder-Decoder architecture X-Translator and achieves a high frame reduction rate as 97.76% with IMU and Wi-Fi data.

Tracking subjects in videos is one of the most widely used functions in camera-based IoT applications such as security surveillance, smart city traffic safety enhancement, vehicle to pedestrian communication and so on. In the computer vision domain, tracking is usually achieved by first detecting subjects with bounding boxes, then associating detected bounding boxes across video frames. For many IoT systems, images captured by cameras are usually sent over the network to be processed at a different site that has more powerful computing resources than edge devices. However, sending entire frames through the network causes significant bandwidth consumption that may exceed the system bandwidth constraints. To tackle this problem, we propose ViFiT, a transformer-based model that reconstructs vision bounding box trajectories from phone data (IMU and Fine Time Measurements). It leverages a transformer ability of better modeling long-term time series data. ViFiT is evaluated on Vi-Fi Dataset, a large-scale multimodal dataset in 5 diverse real world scenes, including indoor and outdoor environments. To fill the gap of proper metrics of jointly capturing the system characteristics of both tracking quality and video bandwidth reduction, we propose a novel evaluation framework dubbed Minimum Required Frames (MRF) and Minimum Required Frames Ratio (MRFR). ViFiT achieves an MRFR of 0.65 that outperforms the state-of-the-art approach for cross-modal reconstruction in LSTM Encoder-Decoder architecture X-Translator of 0.98, resulting in a high frame reduction rate as 97.76%.

In Smart City and Vehicle-to-Everything (V2X) systems, acquiring pedestrians' accurate locations is crucial to traffic safety. Current systems adopt cameras and wireless sensors to detect and estimate people's locations via sensor fusion. Standard fusion algorithms, however, become inapplicable when multi-modal data is not associated. For example, pedestrians are out of the camera field of view, or data from camera modality is missing. To address this challenge and produce more accurate location estimations for pedestrians, we propose a Generative Adversarial Network (GAN) architecture. During training, it learns the underlying linkage between pedestrians' camera-phone data correspondences. During inference, it generates refined position estimations based only on pedestrians' phone data that consists of GPS, IMU and FTM. Results show that our GAN produces 3D coordinates at 1 to 2 meter localization error across 5 different outdoor scenes. We further show that the proposed model supports self-learning. The generated coordinates can be associated with pedestrian's bounding box coordinates to obtain additional camera-phone data correspondences. This allows automatic data collection during inference. After fine-tuning on the expanded dataset, localization accuracy is improved by up to 26%.