Sync crowd-detection from metro-analytics-catalog
Browse files- README.md +10 -7
- export_and_quantize.sh +1 -1
README.md
CHANGED
|
@@ -6,7 +6,7 @@
|
|
| 6 |
|---|---|
|
| 7 |
| **Category** | Object Detection (Crowd / Person Counting) |
|
| 8 |
| **Source Framework** | PyTorch (Ultralytics) |
|
| 9 |
-
| **Supported Precisions** | FP32, FP16,
|
| 10 |
| **Inference Engine** | OpenVINO |
|
| 11 |
| **Hardware** | CPU, GPU, NPU |
|
| 12 |
| **Detected Class** | `person` (COCO class 0) |
|
|
@@ -42,6 +42,10 @@ python3 -m venv .venv --system-site-packages
|
|
| 42 |
source .venv/bin/activate
|
| 43 |
```
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
---
|
| 46 |
|
| 47 |
## Getting Started
|
|
@@ -148,17 +152,16 @@ The `export_and_quantize.sh` script downloads `test.jpg` automatically.
|
|
| 148 |
Re-run the OpenVINO sample above.
|
| 149 |
The script reads `test.jpg`, prints the crowd count to the console, and writes the annotated frame to `output.jpg`.
|
| 150 |
|
| 151 |
-
Expected console output
|
| 152 |
|
| 153 |
```text
|
| 154 |
-
Detected persons:
|
| 155 |
```
|
| 156 |
|
| 157 |
-
`output.jpg` is the same image with a green bounding box drawn around each detected person and the text `Crowd count:
|
| 158 |
|
| 159 |
-
> **Tip:**
|
| 160 |
-
>
|
| 161 |
-
> deployment site showing a representative crowd density.
|
| 162 |
|
| 163 |
### DLStreamer Sample
|
| 164 |
|
|
|
|
| 6 |
|---|---|
|
| 7 |
| **Category** | Object Detection (Crowd / Person Counting) |
|
| 8 |
| **Source Framework** | PyTorch (Ultralytics) |
|
| 9 |
+
| **Supported Precisions** | FP32, FP16, INT8 (mixed-precision) |
|
| 10 |
| **Inference Engine** | OpenVINO |
|
| 11 |
| **Hardware** | CPU, GPU, NPU |
|
| 12 |
| **Detected Class** | `person` (COCO class 0) |
|
|
|
|
| 42 |
source .venv/bin/activate
|
| 43 |
```
|
| 44 |
|
| 45 |
+
> **Note:** The `--system-site-packages` flag is required so the virtual
|
| 46 |
+
> environment can access the system-installed OpenVINO and DLStreamer Python
|
| 47 |
+
> packages.
|
| 48 |
+
|
| 49 |
---
|
| 50 |
|
| 51 |
## Getting Started
|
|
|
|
| 152 |
Re-run the OpenVINO sample above.
|
| 153 |
The script reads `test.jpg`, prints the crowd count to the console, and writes the annotated frame to `output.jpg`.
|
| 154 |
|
| 155 |
+
Expected console output:
|
| 156 |
|
| 157 |
```text
|
| 158 |
+
Detected persons: 4
|
| 159 |
```
|
| 160 |
|
| 161 |
+
`output.jpg` is the same image with a green bounding box drawn around each detected person and the text `Crowd count: 4` overlaid in the top-left corner.
|
| 162 |
|
| 163 |
+
> **Tip:** For production testing, replace the bundled `test.jpg` with an image
|
| 164 |
+
> from your target deployment site showing a representative crowd density.
|
|
|
|
| 165 |
|
| 166 |
### DLStreamer Sample
|
| 167 |
|
export_and_quantize.sh
CHANGED
|
@@ -38,7 +38,7 @@ fi
|
|
| 38 |
|
| 39 |
echo "--- Downloading sample test image ---"
|
| 40 |
if [[ ! -f test.jpg ]]; then
|
| 41 |
-
wget -q -O test.jpg https://
|
| 42 |
echo "Downloaded: test.jpg"
|
| 43 |
else
|
| 44 |
echo "Already present: test.jpg"
|
|
|
|
| 38 |
|
| 39 |
echo "--- Downloading sample test image ---"
|
| 40 |
if [[ ! -f test.jpg ]]; then
|
| 41 |
+
wget -q -O test.jpg https://ultralytics.com/images/bus.jpg
|
| 42 |
echo "Downloaded: test.jpg"
|
| 43 |
else
|
| 44 |
echo "Already present: test.jpg"
|