CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification

By Zheng Tang, Milind R. Naphade, Ming-Yu Liu, Xiaodong Yang, Stan Birchfield, Shuo Wang, Ratnesh Kumar, D. Anastasiu, Jenq-Neng Hwang. Computer Vision and Pattern Recognition, 2019

445 citations recorded by the source corpus.

Urban traffic optimization using traffic cameras as sensors is driving the need to advance state-of-the-art multi-target multi-camera (MTMC) tracking. This work introduces CityFlow, a city-scale traffic camera dataset consisting of more than 3 hours of synchronized HD videos from 40 cameras across 10 intersections, with the longest distance between two simultaneous cameras being 2.5 km. To the best of our knowledge, CityFlow is the largest-scale dataset in terms of spatial coverage and the number of cameras/videos in an urban environment. The dataset contains more than 200K annotated bounding boxes covering a wide range of scenes, viewing angles, vehicle models, and urban traffic flow conditions. Camera geometry and calibration information are provided to aid spatio-temporal analysis. In addition, a subset of the benchmark is made available for the task of image-based vehicle re-identification (ReID). We conducted an extensive experimental evaluation of baselines/state-of-the-art approaches in MTMC tracking, multi-target single-camera (MTSC) tracking, object detection, and image-based ReID on this dataset, analyzing the impact of different network architectures, loss functions, spatio-temporal models and their combinations on task effectiveness. An evaluation server is launched with the release of our benchmark at the 2019 AI City Challenge (https://www.aicitychallenge.org/) that allows researchers to compare the performance of their newest techniques. We expect this dataset to catalyze research in this field, propel the state-of-the-art forward, and lead to deployed traffic optimization(s) in the real world.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9be285ae8994b68868b54c16ab355e93adce41ad

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation (2021, background): “Others learn tracking representations by exploiting the appearance similarity [33, 42, 35] or re-identify vanished objects [17, 36, 37].”
Joint Discriminative and Generative Learning for Person Re-Identification (2019, unknown): “Current state-of-theart re-id methods widely formulate the tasks as deep metric learning problems [13, 55], or use classification losses as the proxy targets to learn deep embeddings [23, 39, 48, 53, 54, 57].”
Multiple object tracking: A literature review (2014, background): “Possible combinations include object segmentation [206, 207, 208, 209], re-identification [210, 194, 211], human pose estimation [18, 212, 213, 214, 215], and action recognition [19].”
The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification (2020, methodology): “With recent breakthroughs due to deep learning, we can easily learn discriminative embeddings for vehicles by feeding images from large-scale vehicle datasets, such as VehicleID, VeRi, VERI-Wild, Vehicle-1M, PKU VD1&VD2 [43], CompCars [44], and CityFlow [40], to train a DCNN that is later used as th”