We collected and annotated 60,000 frames
with rich information, leading to about 900,000 annotated objects.
You can see the the sample annotation on the right
You can try out our sample data by click the button below. it contains data from one camera with three different time window.
All submitted papers or any publicly available text using the CityCam database must cite the following paper:
Shanghang Zhang, Guanhang Wu, João P. Costeira, and José MF Moura, Understanding Traffic Density from Large-Scale Web Camera Data, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4264-4273.
H Zhao, S Zhang, G Wu, JP Costeira, JMF Moura, GJ Gordon, Adversarial Multiple Source Domain Adaptation, Neural Information Processing Systems (NIPS) 2018
S Zhang, G Wu, JP Costeira, JMF Moura, FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras, International Conference on Computer Vision (ICCV) 2017