DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to score each tracked pedestrian's accident probability in a clip with JEV Sees

Get a per-frame probability for every tracked pedestrian in a short traffic video segment.

  • Research
  • Intermediate
  • 30 minutes
  • From the README
  • Any agent

Authorization notice. JEV Sees is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Credentials. Store the JEV API key in your environment only, since each run sends clip frames to the JEV service.

Who it is forA traffic safety analyst reviewing a dashcam or street camera clip who needs to see which pedestrians are judged as involved in a car accident in the current frame.

The problemReviewing many frames by hand to follow each pedestrian and judge their involvement is slow and inconsistent.

The outcomeA table of frame indexes, video times, object IDs, and probabilities for each pedestrian in the chosen segment.

What you need first

  • Python 3.10 or newer
  • A JEV API key from console.typesafe.ai/keys
  • Internet access for the first run, unless the Florence-2 and CLIP weights are already available locally
  • Git and a terminal

Steps

  1. Clone the project with git clone https://github.com/CharlesFeng0314/JEV_sees.git.
  2. Enter the folder with cd JEV_sees.
  3. Install it with python -m pip install -e ..
  4. Set your key on macOS or Linux with export TYPESAFE_API_KEY="your-key", or in PowerShell with $env:TYPESAFE_API_KEY = "your-key".
  5. Run the bundled example with python examples/traffic_relations.py.
  6. To test another segment, change the start and end frame numbers in your own script that calls probability(...).

Prompt for your agent

In the JEV_sees repo at <repo path>, with TYPESAFE_API_KEY set, run examples/traffic_relations.py on assets/traffic.mp4 for frames 504 to 600. Report frame_index, object_id, and probability for each pedestrian; verify that the output describes the current frame and does not forecast future accidents.

Caveat. The README says this asks about the current frame and is not a future-accident forecast, so do not use the output as a prediction.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page