Ask Your Question

nikogamulin's profile - activity

2019-05-03 17:22:40 -0500 asked a question How to detect circular erosion/dilation

How to detect circular erosion/dilation Hi, I would like to detect circular erosions and dilations on a line. For dilat

2019-04-18 11:25:31 -0500 commented question Is there a way to mark the moving points and in the end determine the position of every point?

Python is fine. For beginning there's one camera but later I might add more; could apply stitching - doesn't matter - wh

2019-04-18 08:26:13 -0500 commented question Is there a way to mark the moving points and in the end determine the position of every point?

This is just a hypotethical example. The main thing I would like to solve is to track arbitrary points and assess their

2019-04-18 07:41:39 -0500 asked a question Is there a way to mark the moving points and in the end determine the position of every point?

Is there a way to mark the moving points and in the end determine the position of every point? Hi, Suppose there is a c

2019-04-18 07:41:27 -0500 asked a question Is there a way to mark the moving points and in the end determine the position of every point?

Is there a way to mark the moving points and in the end determine the position of every point? Hi, Suppose there is a c

2019-04-18 07:41:15 -0500 asked a question Is there a way to mark the moving points and in the end determine the position of every point?

Is there a way to mark the moving points and in the end determine the position of every point? Hi, Suppose there is a c

2019-03-18 08:23:46 -0500 edited question Unable to convert retrained TensorFlow model to IR

Unable to convert retrained TensorFlow model to IR Hi, I retrained the ssd_mobilenet_v2_coco to detect custom set of ob

2019-03-18 01:49:24 -0500 edited question Unable to convert retrained TensorFlow model to IR

Unable to convert retrained TensorFlow model to IR Hi, I retrained the ssd_mobilenet_v2_coco to detect custom set of ob

2019-03-18 01:48:23 -0500 edited question Unable to convert retrained TensorFlow model to IR

Unable to convert retrained TensorFlow model to IR Hi, I retrained the ssd_mobilenet_v2_coco to detect custom set of ob

2019-03-17 15:45:04 -0500 asked a question Unable to convert retrained TensorFlow model to IR

Unable to convert retrained TensorFlow model to IR Hi, I retrained the ssd_mobilenet_v2_coco to detect custom set of ob

2018-12-23 04:28:01 -0500 received badge  Supporter (source)
2018-12-23 04:27:52 -0500 marked best answer How to run pretrained model with OpenVINO on RPi

Hi,

After successfully running python face detection example, I tried to modify the code in order to run vehicle and licence plate detection, but the model didn't detect anything. As I haven't figured out what's the issue, I would appreciate any suggestion regarding the problem.

The script I wrote looks as follows:

import cv2

def predict(frame, net):
    # Prepare input blob and perform an inference
    blob = cv2.dnn.blobFromImage(frame, size=(300, 300), ddepth=cv2.CV_8U)
    net.setInput(blob)
    out = net.forward()

    predictions = []

    # The net outputs a blob with the shape: [1, 1, N, 7], where N is the number of detected bounding boxes.
    # For each detection, the description has the format: [image_id, label, conf, x_min, y_min, x_max, y_max]

    # Draw detected faces on the frame
    for detection in out.reshape(-1, 7):
        image_id, label, conf, x_min, y_min, x_max, y_max = detection

        if conf > 0.5:
            predictions.append(detection)

    # return the list of predictions to the calling function
    return predictions

# Load the model
net = cv2.dnn.readNet('models/vehicle-license-plate-detection-barrier-0106.xml', 'models/vehicle-license-plate-detection-barrier-0106.bin')

# Specify target device
net.setPreferableTarget(cv2.dnn.DNN_TARGET_MYRIAD)

# Read an image
frame = cv2.imread('screenshots/mercedes.jpg')

predictions = predict(frame, net)

# Draw detected faces on the frame
for prediction in predictions:
    confidence = float(detection[2])
    xmin = int(detection[3] * frame.shape[1])
    ymin = int(detection[4] * frame.shape[0])
    xmax = int(detection[5] * frame.shape[1])
    ymax = int(detection[6] * frame.shape[0])

    cv2.rectangle(frame, (xmin, ymin), (xmax, ymax), color=(0, 255, 0))

# Save the frame to an image file
cv2.imwrite('out.png', frame)

Basically, I have downloaded the model files from this adddress and then modified input dimensions according to specifications.

To test the detection, I used the image attached below

image description

The model I wanted to test is described here

Update

Now I tried to use vehicle-detection-adas-0002 model and it works. The differences I noticed are in the models:

  • vehicle-license-plate-detection-barrier-0106 is a MobileNetV2 + SSD-based vehicle and license plate detector for the "Barrier" use case

  • vehicle-detection-adas-0002 is a vehicle detection network based on an SSD framework with tuned MobileNet v1 as a feature extractor

So I guess these models might have to be initialized differently.

2018-12-23 04:27:52 -0500 received badge  Scholar (source)
2018-12-22 08:37:44 -0500 commented answer How to run pretrained model with OpenVINO on RPi

Thanks! Why isn't there another bounding box for a car, same as in the example, provided here

2018-12-22 03:48:50 -0500 edited question How to run pretrained model with OpenVINO on RPi

How to run pretrained model with OpenVINO on RPi Hi, After successfully running python face detection example, I tried

2018-12-22 02:43:50 -0500 received badge  Enthusiast
2018-12-21 13:17:40 -0500 edited question How to run pretrained model with OpenVINO on RPi

How to run pretrained model with OpenVINO on RPi Hi, After successfully running python face detection example, I tried

2018-12-21 13:12:51 -0500 edited question How to run pretrained model with OpenVINO on RPi

How to run pretrained model with OpenVINO on RPi Hi, After successfully running python face detection example, I tried

2018-12-21 12:17:11 -0500 received badge  Student (source)
2018-12-21 12:14:59 -0500 asked a question How to run pretrained model with OpenVINO on RPi

How to run pretrained model with OpenVINO on RPi Hi, After successfully running python face detection example, I tried

2016-04-13 10:09:29 -0500 asked a question How to filter objects by color?

Hi,

To detect a black object in a cluttered scene I tried to follow this tutorial. Due to natural light the color of the object (e.g. black) is not uniform on the captured image and therefore it was not possible to filter it out using the method described in the tutorial mentioned above.

Does anyone know what is the best way to detect objects by color in cluttered scene?

Thanks!

2016-04-12 02:34:08 -0500 commented question Why the trained model's performance is not the same while running on PC and Android?

@Tetragramm thanks for reminding me to clarify the question!

2016-04-12 02:28:53 -0500 received badge  Editor (source)
2016-04-11 02:41:45 -0500 asked a question Why the trained model's performance is not the same while running on PC and Android?

Hi,

I have trained a cascade classifier for a particular object. The classifier is supposed to be used in android app. For testing purposes I've written a python script and the model performance seemed great running it on PC. Then, when I tried to use the same model in android app, the performance was poor, both, in terms of speed and accuracy. Does anyone know what could be the cause for different accuracy of the same model?

Thanks!