Over the past few years, several methods for trajectory-based activity forecasting have been proposed. However, most techniques have been evaluated on a limited number of sequences. Further, these methods have either been evaluated on different subsets of the available data, using different evaluation scripts, or on contrasting coordinate systems (2D, 3D). These inconsistencies have made it difficult to objectively compare forecasting techniques. One potential solution involves creating a standardized benchmark to serve as an objective measure of performance; despite their potential pitfalls, benchmarks hold great promise in addressing such comparison issues. There have been a limited number of attempts at trajectory forecasting benchmarks, such as the ETH and the UCY datasets. However, a common technique for presenting forecasting results requires both a standard dataset and evaluation metrics. We introduce TrajNet, a new, large scale trajectory-based activity benchmark, that uses a unified evaluation system to test gathered state-of-the-art methods on various trajectory-based activity forecasting datasets. Our benchmark not only covers a wide range of datasets, but also includes various types of targets, from pedestrians to bikers, skateboarders, cars, buses, and golf cars, that navigate in a real world outdoor environment.

We have created a framework for the fair evaluation of multiple trajectory forecasting algorithms. In this framework we provide:

Datasets

A large collection of datasets, some already in use and some new challenging sequences!

Comparsion

An easy way to compare state-of-the-art predictors.

Benchmark

A common evaluation tool providing several measures, from recall to precision to running time.

Detection

Detections for all the sequences.

Challenges

Several challenges with subsets of data for specific tasks such as 3D tracking and surveillance.

Coming Soon...

We're adding new features every day!

We rely on the spirit of crowdsourcing, and we encourage researchers to submit their sequences to our benchmark, so the quality of multiple object tracking systems can keep increasing and tackling more challenging scenarios.

• Alpha version of the benchmark created for local testing
• Benchmark template created from MOTChallenge

The datasets provided on this page are published under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 License. This means that you must attribute the work in the manner specified by the authors, you may not use this work for commercial purposes and if you alter, transform, or build upon this work, you may distribute the resulting work only under the same license. If you are interested in commercial usage you can contact us for further options.

If you are using this dataset in your research, please use the bibtex listed below to cite us:

@article{sadeghiankosaraju2018trajnet,
  title={TrajNet: Towards a Benchmark for Human Trajectory Prediction},
  author={Sadeghian, Amir and Kosaraju, Vineet and Gupta, Agrim and Savarese, Silvio and Alahi, Alexandre},
  journal={arXiv preprint},
  volume={},
  number={},
  pages={},
  year={2018}
}