Object Detection on an RTSP Stream

Guides
3

Hi @iulian_paul_NAIDIN
Welcome to the Hailo community.

There are two methods to detect just one category:

  1. Filter the results as below:
import degirum as dg, degirum_tools

inference_host_address = "@local"
zoo_url = 'degirum/hailo'
token=''
device_type=['HAILORT/HAILO8L']

model_name = "yolov8n_relu6_coco--640x640_quant_hailort_hailo8l_1"
image_source = "<path to image>"
classes = {"car"}

# load model with set desired classes for output
model = dg.load_model(
    model_name=model_name,
    inference_host_address=inference_host_address,
    zoo_url=zoo_url,
    token=token,
    output_class_set = classes
)

# Run AI model on image
inference_result = model(image_source)

# print AI inference results
print(inference_result)

# AI prediction: show only desired classes
with degirum_tools.Display("All classes (press 'q' to exit)") as output_display:
    output_display.show_image(inference_result)
  1. Run a custom model that detects only that class.

Yes, you can use your own YOLOv8 model to work with DeGirum PySDK. See our user guide: User Guide 3: Simplifying Object Detection on a Hailo Device Using DeGirum PySDK. Please let us know if you need any help.