Find Objects in a Street Photo with DETR

The useful part

Object Detection Web is featured here for one specific job: dETR object labels and bounding-box predictions. This guide focuses on that workflow so you can decide whether it fits your task before trying it.

What happened in the demo

Open Object Detection Web and choose its built-in example. We’re using this street photo for a fictional workshop, with no upload needed. Now inspect the real result: boxes labeled car, person, bicycle, and traffic light. DETR predicts both object names and their locations. These are predictions, so check them against the photo yourself.

The example used in the reel

A small, specific input makes the result easier to inspect. Use the example below to understand the scope of the recorded workflow; it is not a promise that a new run will produce an identical result.

Use the built-in city-streets photo and inspect the actual model bounding boxes.

Try it yourself

1. Load the street photograph
2. Run the detector
3. Inspect the boxes, class labels and confidence values

Start with material you own or have permission to use. Save the original and compare it with the output before moving the result into a real project. If the interface has changed, follow the current official instructions linked below.

What to check before using the result

Boxes and labels can miss or misidentify objects. Check them against the visible scene.

Keep the task narrow on your first attempt. Check the details that matter to your use case rather than judging only whether the result looks polished. A successful short example is a useful introduction, not a benchmark of the whole product.

Access, free demos & limits

Free browser demonstration verified in the recorded example on 2026-10-30. Official Space was listed as Running during live research. Its public source implements the built-in example without an account or payment flow. Initial model loading requires time and internet access; no paid service is needed for this demonstration.

Availability notes refer to the dated demonstration or source check. Features, limits and sign-in requirements can change. Check the official site before starting a larger project.

Sources & context

• huggingface.co/spaces/Xenova/object-detection-web ↗Source checked 2026-10-30
• huggingface.co/spaces/Xenova/object-detection-web/blob/main/index.js ↗Source checked 2026-10-30
• huggingface.co/spaces/Xenova/object-detection-web/blob/main/index.html ↗Source checked 2026-10-30

This guide expands the channel’s recorded example and the official sources checked for that reel. Generated results are examples, not endorsements or guarantees. Read our editorial policy.