Zoran Kostic

As smart cities evolve, privacy-preserving edge processing at traffic intersections has become essential for real-time safety applications while reducing data transmission and centralized computation. High-altitude cameras with on-device inference provide an optimal solution that respects privacy while delivering low-latency results. We introduce Constellation, a dataset of 13K images for research on object detection in dense urban streetscapes from high-elevation cameras across varied temporal conditions. The dataset addresses challenges in small object detection, particularly for pedestrians observed from elevated positions with limited pixel footprints. Our evaluation of contemporary object detection architectures reveals a 10% lower average precision (AP) for small pedestrians compared to vehicles. Pretraining models on structurally similar datasets increases mean AP by 1.8%. Domain-specific data augmentations and pseudo-labeled data from top-performing models further enhance performance. We evaluate deployment viability on resource-constrained edge devices including Jetson Orin, Raspberry Pi 5, and mobile platforms, demonstrating feasibility of privacy-preserving on-device processing. Comparing models trained on data collected across different time intervals reveals performance drift due to changing intersection conditions. The best-performing model achieves 92.0% pedestrian AP with 7.08 ms inference time on A100 machines, and 95.4% mAP. The best-performing edge model achieves a similar performance, with Jetson Orin Nano achieving 94.5% mAP and 27.5ms inference time using TensorRT.

We present methods and applications for the development of digital twins (DT) for urban traffic management. While the majority of studies on the DT focus on its “eyes,” which is the emerging sensing and perception like object detection and tracking, what really distinguishes the DT from a traditional simulator lies in its “brain,” the prediction and decision making capabilities of extracting patterns and making informed decisions from what has been seen and perceived. In order to add value to urban transportation management, DTs need to be powered by artificial intelligence and complement with low-latency high-bandwidth sensing and networking technologies, in other words, cyberphysical systems. This paper can be a pointer to help researchers and practitioners identify challenges and opportunities for the development of DTs; a bridge to initiate conversations across disciplines; and a road map to exploiting potentials of DTs for diverse urban transportation applications.

Tracking the precise movement of surgical tools is essential for enabling automated analysis, providing feedback, and enhancing safety in robotic-assisted surgery. Accurate 3D tracking of surgical tooltips is challenging to implement when using monocular videos due to the complexity of extracting depth information. We propose a pipeline that combines state-of-the-art foundation models—Florence2 and Segment Anything 2 (SAM2)—for zero-shot 2D localization of tooltip coordinates using a monocular video input. Localization predictions are refined through supervised training of the YOLOv11 segmentation model to enable real-time applications. The depth estimation model Metric3D computes the relative depth and provides tooltip camera coordinates, which are subsequently transformed into world coordinates via a linear model estimating rotation and translation parameters. An experimental evaluation on the JIGSAWS Suturing Kinematic dataset achieves a 3D Average Jaccard score on tooltip tracking of 84.5 and 91.2 for the zero-shot and supervised approaches, respectively. The results validate the effectiveness of our approach and its potential to enhance real-time guidance and assessment in robotic-assisted surgical procedures.

Blind and low-vision (BLV) people rely on GPS-based systems for outdoor navigation. GPS’s inaccuracy, however, causes them to veer off track, run into obstacles, and struggle to reach precise destinations. While prior work has made precise navigation possible indoors via hardware installations, enabling this outdoors remains a challenge. Interestingly, many outdoor environments are already instrumented with hardware such as street cameras. In this work, we explore the idea of repurposing existing street cameras for outdoor navigation. Our community-driven approach considers both technical and sociotechnical concerns through engagements with various stakeholders: BLV users, residents, business owners, and Community Board leadership. The resulting system, StreetNav, processes a camera’s video feed using computer vision and gives BLV pedestrians real-time navigation assistance. Our evaluations show that StreetNav guides users more precisely than GPS, but its technical performance is sensitive to environmental occlusions and distance from the camera. We discuss future implications for deploying such systems at scale.

We introduce Constellation, a dataset of 13K images suitable for research on detection of objects in dense urban streetscapes observed from high-elevation cameras, collected for a variety of temporal conditions. The dataset addresses the need for curated data to explore problems in small object detection exemplified by the limited pixel footprint of pedestrians observed tens of meters from above. It enables the testing of object detection models for variations in lighting, building shadows, weather, and scene dynamics. We evaluate contemporary object detection architectures on the dataset, observing that state-of-the-art methods have lower performance in detecting small pedestrians compared to vehicles, corresponding to a 10% difference in average precision (AP). Using structurally similar datasets for pretraining the models results in an increase of 1.8% mean AP (mAP). We further find that incorporating domain-specific data augmentations helps improve model performance. Using pseudo-labeled data, obtained from inference outcomes of the best-performing models, improves the performance of the models. Finally, comparing the models trained using the data collected in two different time intervals, we find a performance drift in models due to the changes in intersection conditions over time. The best-performing model achieves a pedestrian AP of 92.0% with 11.5 ms inference time on NVIDIA A100 GPUs, and an mAP of 95.4%.