About COCO-SSD Object Detection Demo
COCO-SSD is an object detection model trained on the COCO dataset, and this page runs it with TensorFlow.js on an image you choose, so you can see its labels, boxes and scores yourself. It opens with the more accurate of the two bases, mobilenet_v2 (about 67 MB), and you can switch to the lite one (about 18 MB). It is free, needs no sign-up and runs in your browser, so nothing you enter is uploaded.
SSD stands for single-shot multibox detector: the model looks at the image once and predicts boxes and class scores together, which is why it is fast enough for a browser. COCO stands for Common Objects in Context, a large image dataset with 80 labelled object classes, listed in the table below. A detection is a bounding box, one of those 80 labels and a score between 0 and 1, shown here as a percentage.
It is a good way to see what a small model can and cannot recognise, and to compare its two bases on the same picture: lite_mobilenet_v2 is the smallest and fastest, mobilenet_v2 is slower and more accurate. It tends to do well with large, clear objects such as people, cars and chairs, and to miss small, crowded or partly hidden ones. It will not name anything outside the 80 classes and it is not YOLO, which is a different family of detectors. The page asks the model for up to 100 boxes per image, down to a score of 5%, and the slider and box limit decide which of them you see.
How to use COCO-SSD Object Detection Demo
- Choose Image or Webcam, then choose a model. The size of each is shown.
- The small model loads by itself when the page opens, unless Data Saver is on; for the larger one press Download model and confirm. The card says when you can start.
- For an image, drop a picture on the box, tap it to choose one, paste one with Ctrl or Cmd + V, or press Take a photo on a phone.
- For the webcam, press Start camera and allow camera access in your browser.
- Read the boxes on the picture and the text list of detections below it, which gives each label, score and box in pixels.
- Move the Minimum score slider (5% to 95%) or change the box limit (1 to 100) to show fewer or more boxes without detecting again.
- For an image, press Download PNG to save the annotated picture at full resolution.
Features
- Detects 80 COCO object classes with a bounding box, a label and a score for each.
- Two models to choose from: Lite (fast) (about 18 MB, faster) and Accurate (about 67 MB, more accurate), with the download size shown first.
- Detects on the full-resolution image or on a copy up to 2048 px, with the boxes scaled back to the original.
- Image input by drop, file choice, paste or the phone camera.
- Webcam mode that draws video and boxes straight to the canvas in an animation loop, so the page is not re-rendered for every frame. Its text summary updates about four times a second.
- A minimum score slider and a limit on the number of boxes, applied instantly to results that are already found.
- A text list of every detection for screen readers, and a description on the canvas itself.
- Download of the annotated image as a PNG at the full size of the original.
- A built-in list of the 80 detectable objects.
- The camera stops when you press Stop camera, switch to Image mode or leave the page.
The 80 classes COCO-SSD knows
| Classes | Labels |
|---|---|
| 1 to 10 | person, bicycle, car, motorcycle, airplane, bus, train, truck, boat, traffic light |
| 11 to 20 | fire hydrant, stop sign, parking meter, bench, bird, cat, dog, horse, sheep, cow |
| 21 to 30 | elephant, bear, zebra, giraffe, backpack, umbrella, handbag, tie, suitcase, frisbee |
| 31 to 40 | skis, snowboard, sports ball, kite, baseball bat, baseball glove, skateboard, surfboard, tennis racket, bottle |
| 41 to 50 | wine glass, cup, fork, knife, spoon, bowl, banana, apple, sandwich, orange |
| 51 to 60 | broccoli, carrot, hot dog, pizza, donut, cake, chair, couch, potted plant, bed |
| 61 to 70 | dining table, toilet, tv, laptop, mouse, remote, keyboard, cell phone, microwave, oven |
| 71 to 80 | toaster, sink, refrigerator, book, clock, vase, scissors, teddy bear, hair drier, toothbrush |
Good to know
About the model download
Your images and camera frames are never uploaded. The pretrained detection model, however, is downloaded from Google model hosting, the lite model in the background when the page opens and the accurate one when you press Download model (about 18 MB for the lite model, about 67 MB for the accurate one), so it needs an internet connection to load and is not an offline tool. After it has loaded, detection runs on your device.
Privacy: how it works
- Images and webcam frames are processed in your browser and are never uploaded to Ulkaa or to anyone else. The camera stream is not recorded or stored.
- One download is needed: the pretrained COCO-SSD weights come from Google model hosting after you press Download model (about 18 MB or 67 MB). That request does not include your images. The TensorFlow.js code and the COCO-SSD code are part of this site.
Tips
- Use a clear, well-lit picture where the object takes up a good part of the frame. Small or blurry objects are often missed.
- If you see wrong labels, raise the minimum score. If objects are missing, lower it, but expect more false boxes.
- Try the accurate model if the lite one misses small objects. It takes longer to download and to run.
- In webcam mode, allow camera access when your browser asks. Camera access needs a secure (https) page.
- Stop the camera when you are finished. Detection runs continuously while it is on, which uses processor power and battery.
- On a phone, Take a photo opens the rear camera. To pick from your gallery, tap the drop box instead.
Frequently asked questions
Is it really free?
Yes. There is no price, no trial and no credit card. Ulkaa Tool does the work with your own device, so there is no server bill to pass on to you.
Do I need an account?
No. There is no sign-up and no login. Open the page and use it. An Ulkaa account is not needed for anything on this tool.
Does it run in my browser?
Yes. Your images are processed by code running in your browser tab, on your own device.
Is my data uploaded?
No. Your images are never sent to Ulkaa or to anyone else. You can check this yourself by watching the Network tab in your browser developer tools while you use the tool.
What is COCO-SSD?
It is a single-shot object detection model trained on the COCO dataset. It finds objects in an image and gives each one a label from 80 classes, a box and a score.
Is COCO-SSD the same as YOLO?
No. Both are single-pass detectors, but they are different models with different training and accuracy. This page runs COCO-SSD only.
What is the difference between lite_mobilenet_v2 and mobilenet_v2?
They are two backbones for the same detector. lite_mobilenet_v2 is the smaller download (about 18 MB) and faster. mobilenet_v2 is about 67 MB and slower, and is the more accurate of the two.
Can I train it on my own objects?
No. The page uses the pretrained model as it is. It cannot learn new classes.
Where does the model come from?
The pretrained weights are downloaded from Google model hosting, the small one automatically and the larger one after a tap. The code that runs them is part of this site.
More Online Object Detector pages
- Online Object DetectorDetect and label everyday objects in a photo or your webcam with the COCO-SSD model, running in your browser.
- Image Object Detection OnlineFind and label the objects in a photo you choose, paste or take.
- Webcam Object DetectionLive object detection on your camera feed, in the browser.