Unity Perception JSON
Unity Perception is a toolkit for generating datasets for computer vision by using 3D renders.
Overview
Enhancing your dataset with synthetic data can be a powerful tactic for improving your model. Synthetic images are cheaper to generate than collecting and labeling images from the real world and their annotations are guaranteed to be consistently labeled and pixel-perfect every time.
Unity Perception (opens in a new tab) is one tool that can be used to generate training data from 3D models. But their export format isn't supported by any machine learning models. Roboflow can convert these files for easy use and help you combine them with your existing dataset to create a composite dataset that is better than the sum of its parts.
Format Description
Below, learn the structure of Unity Perception JSON.
captures_000.jsonJSON
{
"version": "0.0.1",
"captures": [{
"id": "b49f1317-f3ce-42e3-8201-b85b0bd1574b",
"sequence_id": "96bf8ade-5d77-49a4-82e2-dc1ef567ab82",
"step": 0,
"timestamp": 10.0,
"sensor": {
"sensor_id": "edf45916-afec-9881-8d21-922241c54310",
"ego_id": "1ceb788a-8155-4860-99da-2b406536f198",
"modality": "camera",
"translation": [
0.0,
0.0,
0.0
],
"rotation": [
0.0,
0.0,
0.0,
1.0
],
"camera_intrinsic": [
[
0.999999762,
0.0,
0.0
],
[
0.0,
1.77777731,
0.0
],
[
0.2,
0.266666651,
-1.0006001
]
]
},
"ego": {
"ego_id": "1ceb788a-8155-4860-99da-2b406536f198",
"translation": [
-595.11,
1175.75,
487.64
],
"rotation": [
0.0778284,
0.9212198,
-0.246840149,
0.290459484
],
"velocity": null,
"acceleration": null
},
"filename": "RGB2327d665-d71f-4c4f-8c77-66df8fa29202/rgb_2.png",
"format": "PNG",
"annotations": [{
"id": "a6aef966-1fb3-4d59-91df-a44866e81038",
"annotation_definition": "f9f22e05-443f-4602-a422-ebe4ea9b55cb",
"values": [{
"label_id": 1,
"label_name": "person",
"instance_id": 2,
"x": 875.0,
"y": 303.0,
"width": 151.0,
"height": 122.0
},
{
"label_id": 1,
"label_name": "person",
"instance_id": 3,
"x": 1226.0,
"y": 382.0,
"width": 181.0,
"height": 130.0
},
{
"label_id": 1,
"label_name": "person",
"instance_id": 1,
"x": 660.0,
"y": 402.0,
"width": 148.0,
"height": 112.0
},
{
"label_id": 1,
"label_name": "person",
"instance_id": 5,
"x": 1003.0,
"y": 381.0,
"width": 148.0,
"height": 141.0
},
{
"label_id": 1,
"label_name": "person",
"instance_id": 42,
"x": 831.0,
"y": 389.0,
"width": 230.0,
"height": 225.0
}
]
}]
},
{
"id": "87182978-7b34-4157-85f2-9fa0b57af085",
"sequence_id": "96bf8ade-5d77-49a4-82e2-dc1ef567ab82",
"step": 1,
"timestamp": 20.0,
"sensor": {
"sensor_id": "edf45916-afec-9881-8d21-922241c54310",
"ego_id": "1ceb788a-8155-4860-99da-2b406536f198",
"modality": "camera",
"translation": [
0.0,
0.0,
0.0
],
"rotation": [
0.0,
0.0,
0.0,
1.0
],
"camera_intrinsic": [
[
0.999999762,
0.0,
0.0
],
[
0.0,
1.77777731,
0.0
],
[
0.2,
0.266666651,
-1.0006001
]
]
},
"ego": {
"ego_id": "1ceb788a-8155-4860-99da-2b406536f198",
"translation": [
-595.11,
1175.75,
487.64
],
"rotation": [
0.0778284,
0.9212198,
-0.246840149,
0.290459484
],
"velocity": null,
"acceleration": null
},
"filename": "RGB2327d665-d71f-4c4f-8c77-66df8fa29202/rgb_3.png",
"format": "PNG",
"annotations": [{
"id": "94bffb82-7753-4d79-8294-66e2976d7362",
"annotation_definition": "f9f22e05-443f-4602-a422-ebe4ea9b55cb",
"values": [{
"label_id": 1,
"label_name": "person",
"instance_id": 2,
"x": 875.0,
"y": 303.0,
"width": 151.0,
"height": 122.0
},
{
"label_id": 1,
"label_name": "person",
"instance_id": 3,
"x": 1226.0,
"y": 382.0,
"width": 181.0,
"height": 130.0
},
{
"label_id": 1,
"label_name": "person",
"instance_id": 1,
"x": 660.0,
"y": 402.0,
"width": 148.0,
"height": 112.0
},
{
"label_id": 1,
"label_name": "person",
"instance_id": 5,
"x": 1003.0,
"y": 381.0,
"width": 149.0,
"height": 142.0
},
{
"label_id": 1,
"label_name": "person",
"instance_id": 42,
"x": 831.0,
"y": 389.0,
"width": 230.0,
"height": 225.0
},
{
"label_id": 1,
"label_name": "person",
"instance_id": 4,
"x": 1317.0,
"y": 455.0,
"width": 201.0,
"height": 166.0
},
{
"label_id": 1,
"label_name": "person",
"instance_id": 33,
"x": 454.0,
"y": 462.0,
"width": 213.0,
"height": 216.0
},
{
"label_id": 1,
"label_name": "person",
"instance_id": 13,
"x": 899.0,
"y": 504.0,
"width": 308.0,
"height": 286.0
},
{
"label_id": 1,
"label_name": "person",
"instance_id": 16,
"x": 222.0,
"y": 501.0,
"width": 189.0,
"height": 290.0
},
{
"label_id": 4,
"label_name": "hard-hat",
"instance_id": 38,
"x": 295.0,
"y": 685.0,
"width": 113.0,
"height": 173.0
},
{
"label_id": 1,
"label_name": "person",
"instance_id": 10,
"x": 40.0,
"y": 630.0,
"width": 202.0,
"height": 252.0
},
{
"label_id": 12,
"label_name": "car",
"instance_id": 46,
"x": 827.0,
"y": 712.0,
"width": 257.0,
"height": 229.0
},
{
"label_id": 1,
"label_name": "person",
"instance_id": 26,
"x": 1402.0,
"y": 810.0,
"width": 254.0,
"height": 187.0
},
{
"label_id": 13,
"label_name": "bicycle",
"instance_id": 7,
"x": 667.0,
"y": 641.0,
"width": 298.0,
"height": 394.0
},
{
"label_id": 5,
"label_name": "door",
"instance_id": 31,
"x": 1143.0,
"y": 839.0,
"width": 652.0,
"height": 241.0
}
]
}]
}]
}Convert Data from Unity Perception JSON
- COCO JSON
- COCO Run-Length Encoding (RLE)
- CreateML JSON
- Florence-2
- Google Cloud AutoML Vision CSV
- meituan/yolov6
- Multiclass Classification CSV
- OpenAI CLIP Classification
- OpenAI GPT-4o Object Detection JSONL
- PaliGemma JSONL
- Pascal VOC XML
- RetinaNet Keras CSV
- Sagemaker GroundTruth Manifest
- Scaled-YOLOv4 TXT
- Segment Anything 2
- Tensorflow Object Detection CSV
- Tensorflow TFRecord
- YOLO Darknet TXT
- YOLO Keras TXT
- YOLOv10 PyTorch TXT
- YOLOv11 PyTorch TXT
- YOLOv4 PyTorch TXT
- YOLOv5 Oriented Bounding Boxes
- YOLOv5 PyTorch TXT
- YOLOv7 PyTorch TXT
- YOLOv8 Oriented Bounding Boxes
- YOLOv8 PyTorch TXT
- YOLOv9 PyTorch TXT