count objects per frame

[bongpigeon]

hi! Is there any way I can count objects per frame? I don't want to track them just want to count the objects.

[marcoslucianops]

Take a look on: https://github.com/NVIDIA-AI-IOT/deepstream_python_apps

You can use this repo as pgie on the code and get the number of objects using frame_meta.num_obj_meta.

[bongpigeon]

if I use the python-apps, can I use YOLOv8 which is in your github repo?

[bongpigeon]

can you tell me more specific? I'm using yolov8 for detection and you're saying I can use deepstream-test-1 in my jetson board?

[marcoslucianops]

Yes, just set

pgie.set_property('config-file-path', "config_infer_primary_yoloV8.txt")

With the path of the config_infer_primary_yoloV8.txt file.

[bongpigeon]

do i need to use python-app? Is there anyway I can just edit some parts of your repo?

[bongpigeon]

plus if you see the deepstream-test files, you can see deepstream_test_app.c files in each sample apps. How does this repo work without deepstream_test_app.c files?

[bongpigeon]

static GstPadProbeReturn osd_sink_pad_buffer_probe (GstPad pad, GstPadProbeInfo info, gpointer u_data) { GstBuffer buf = (GstBuffer ) info->data; guint num_rects = 0; NvDsObjectMeta obj_meta = NULL; guint vehicle_count = 0; guint person_count = 0; NvDsMetaList l_frame = NULL; NvDsMetaList l_obj = NULL; NvDsDisplayMeta display_meta = NULL;

NvDsBatchMeta *batch_meta = gst_buffer_get_nvds_batch_meta (buf);

for (l_frame = batch_meta->frame_meta_list; l_frame != NULL;
  l_frame = l_frame->next) {
    NvDsFrameMeta *frame_meta = (NvDsFrameMeta *) (l_frame->data);
    int offset = 0;
    for (l_obj = frame_meta->obj_meta_list; l_obj != NULL;
            l_obj = l_obj->next) {
        obj_meta = (NvDsObjectMeta *) (l_obj->data);
        if (obj_meta->class_id == PGIE_CLASS_ID_VEHICLE) {
            vehicle_count++;
            num_rects++;
        }
        if (obj_meta->class_id == PGIE_CLASS_ID_PERSON) {
            person_count++;
            num_rects++;
        }
    }
    display_meta = nvds_acquire_display_meta_from_pool(batch_meta);
    NvOSD_TextParams *txt_params  = &display_meta->text_params[0];
    display_meta->num_labels = 1;
    txt_params->display_text = g_malloc0 (MAX_DISPLAY_LEN);
    offset = snprintf(txt_params->display_text, MAX_DISPLAY_LEN, "Person = %d ", person_count);
    offset = snprintf(txt_params->display_text + offset , MAX_DISPLAY_LEN, "Vehicle = %d ", vehicle_count);

    /* Now set the offsets where the string should appear */
    txt_params->x_offset = 10;
    txt_params->y_offset = 12;

    /* Font , font-color and font-size */
    txt_params->font_params.font_name = "Serif";
    txt_params->font_params.font_size = 10;
    txt_params->font_params.font_color.red = 1.0;
    txt_params->font_params.font_color.green = 1.0;
    txt_params->font_params.font_color.blue = 1.0;
    txt_params->font_params.font_color.alpha = 1.0;

    /* Text background color */
    txt_params->set_bg_clr = 1;
    txt_params->text_bg_clr.red = 0.0;
    txt_params->text_bg_clr.green = 0.0;
    txt_params->text_bg_clr.blue = 0.0;
    txt_params->text_bg_clr.alpha = 1.0;

    nvds_add_display_meta_to_frame(frame_meta, display_meta);
}

g_print ("Frame Number = %d Number of objects = %d "
        "Vehicle Count = %d Person Count = %d\n",
        frame_number, num_rects, vehicle_count, person_count);
frame_number++;
return GST_PAD_PROBE_OK;

}

I think I can use this code from deepstream_test1.c but I don't know how to put it to. Can you help me?

[marcoslucianops]

do i need to use python-app? Is there anyway I can just edit some parts of your repo?

If you want to use the code in Python.

plus if you see the deepstream-test files, you can see deepstream_test_app.c files in each sample apps. How does this repo work without deepstream_test_app.c files?

This repo works with any DeepStream code. As first use, this repo shows how to run it in the deepstream-app. It's already built when you install the DeepStream SDK.

I think I can use this code from deepstream_test1.c but I don't know how to put it to. Can you help me?

You need to edit hte part you wnat, compile the entire code, and run you compiled application.