Questions tagged [object-detection]

Object detection deals with recognizing the presence of objects of a certain semantic class (e.g. “humans”, “buildings”, “cars”, &c) in digital image and video data.

-8
votes
0answers
24 views

Detect Objects in Image/Photo, using PHP or Javascript

I need to find a simple way of detecting objects in a photo/image and counting them. Example Image: I want to be able to detect a count of 12. Is there a way to do this with PHP or JavaScript ? Any ...
0
votes
0answers
11 views

Detect PDF 417 barcode from the card

I am trying to detect PDF417 barcode from the card. I need the four corner points of the barcode. So that I could do do a prespective transformation.
0
votes
1answer
23 views

Why is the Average Precision of my TensorFlow model -1.000?

I've been training an object_detection TensorFlow model for a while now, but I've noticed that the evaluation table always shows a value of -1.000, whereas I've seen other peoples' outputs display ...
1
vote
2answers
43 views

Can we replace anchor boxes in object detection with multiple bounding box predictors?

A lot of popular and state of the art object detection algorithms like YOLO and SSD use the concepts of anchor boxes. As far as I understand for networks like YOLO v3, each output grid cell has ...
0
votes
0answers
14 views

Transfer learning in Pytorch using fasterrcnn_resnet50_fpn

I am looking for Object Detection for custom dataset in PyTorch. Tutorial here provides a snippet to use pre-trained model for custom object classification model_ft = models.resnet18(pretrained=True)...
0
votes
1answer
33 views

How to use openCV in Xamarin?

I am creating a Xamarin project to detect some objects in images . I want to use openCV library , but I can't wrap it to the xamarin . I wrapped it to an windows form application but I can not wrap ...
-1
votes
0answers
15 views

Yolo V3 in Google Colab

I have been trying to develop an object detection system using Yolo v3 on google Colab instead of my local machine because of its free, fast and open source nature. But the problem is I am getting ...
0
votes
1answer
15 views

Can I save the output images of TensorFlow Objectdetection API in a folder?

I am new to object detection. Can I save the output images of my tensorflow object detection API in a folder after detection is completed in the Jupyter notebook? It was intuitive to right click and ...
0
votes
0answers
18 views

Vine Row Detection in Noisy Image

I'm trying to detect vine rows to use in plant health detection and crop yield in an image that contains a lot of trees, other vegetation and insignificant objects. The objects and trees can be in ...
0
votes
0answers
18 views

Detecting small objects with MobileNet and Faster RCNN

I'm working on object detection of various sorts of animals using the Tensorflow Object Detection API. In the past I successfully applied MobileNet v1 to various settings and I used to be happy with ...
1
vote
1answer
30 views

How to pass arguments to already loaded tensorflow graph ( in memory )

I have an object detection model trained using ssd-mobilenet architecture. I am driving inference in real time from this model using my webcam. The output is a bounding box overlayed on the image ...
0
votes
1answer
19 views

How to use front camera in tensorflow object detection api on android demo

I want to use the front camera in the android demo of tensorflow , what should i change in the code cause im not really familiar with android. This is the code i changed but didn't solve the problem ...
0
votes
0answers
16 views

How can I get the accuracy for single images?

I've trained an object detection model and want to have a look at what kind of images have a low accuracy. How could I do this? This is my first project with Tensorflow as well as with the object ...
0
votes
0answers
11 views

Depth map used for foreground object extraction?

I want to extract the foreground object regions from an image. My idea was to achieve this using depth map prediction. Based on the depth map score , I can extract the regions which will eventually be ...
0
votes
2answers
47 views

What is the best way for object detection in an image in xamarin?

I need to make object detection in my xamarin project . so what is the best way to do it , I prefer that it is free , if not what is the cost of it please ? I checked some links and videos and I ...
1
vote
1answer
25 views

What's the purpose of using a max pooling layer with stride 1 on object detection

I am working with Single Shot Detector (SSD) and more specifically this implementation in keras. As I was examining SSD300 (this also applies to SSD512 as I noticed though) I noticed that after each ...
-2
votes
0answers
24 views

Unable to Proceed With the Tensorflow Object Detection Training

I've followed the guidelines from here I am unable to proceed with the training process The following are the 2 commands tried:- python legacy/train.py --logtostderr --train_dir=training/ --...
-1
votes
0answers
22 views

Is Tensorflow Object Detection API a good solution to find defects for printing press?

I want to find defect for printed object, where I am using a good quality of camera to capture printed object. Scenario : => There will be a master copy. => This master copy need to be checked ...
1
vote
1answer
20 views

Tensorflow Object Detection - mAP steady, but Total Loss is dropping. Keep training?

Training an Object Detection classifier with Tensorflow 1.12.2 and Python 3.6. Using about 20,000 images over 4 classes, and after 160K steps the mAP is pretty steady, but the Total Loss is still ...
0
votes
0answers
25 views

How to draw a rectangle in terminal using asciiplotlib if I know the coordinates of rectangle?

I have coordinates of a rectangle (say p1,p2,p3,p4) and needs to draw the rectangle in terminal using asciiplotlib python library import asciiplotlib as apl import numpy x = numpy.linspace(0, 2 * ...
0
votes
0answers
14 views

How to save google cloud object-tracking video?

Currently working my way through the google cloud video intelligence API -tutorial here: https://cloud.google.com/video-intelligence/docs/object-tracking The output gives me details on the bounding ...
0
votes
0answers
41 views

How can I detect a ball using its shape with opencv? [on hold]

For my thesis I have to detect a soccer ball using the stream of a match. I managed to reduce the candidates using color features, but I still have too many candidates. How can I detect the ball ...
-1
votes
0answers
21 views

Need help in Training Yolov3 model on a new object class

How to train an object detection model on a new class with custom data? I want to train a yolov3 model on two classes which are Person and dustbin. As there are weights which are already trained on ...
-3
votes
0answers
16 views

Small circle holes detection in metal mesh

Given a set of 6 images. Each images is a silver mesh with holes inside. There were 6 label files comes together for each image. Content of image is structured like this: HoleN|X-coordinate of ...
0
votes
1answer
21 views

From what aspect to measure the performance of an object detector?

I am on the hook to measure the prediction results of an object detector. I learned from some tutorials that when testing a trained object detector, for each object in the test image, the following ...
0
votes
0answers
8 views

Turicreate model training is not using the full GPU

I am trying to train a object detector model using turicreate, but it is not using the full system resources and I think it is taking more time to train the model. Is there any setting which can make ...
-2
votes
0answers
14 views

UTM coordinates to Pixel coordniates

I'm preparing a labeled data for training, it is composite into satellite images with associated shape file of polygons-rectangles (Bounding Box). But the main problem that i have, is the points ...
0
votes
0answers
12 views

has ssd_mobilenet_v1_coco_2017_11_17 been trained on labelled dataset?

Has the COCO dataset been labeled on this pre-trained model? I am trying to figure out if the object detection that happens after using this pre-trained model is actually an output of an unlabelled ...
0
votes
0answers
8 views

How can i make a stream of images from my video(video processing/person detection using tensorflow).The code is run in google colab

I am trying to identify people from the video and wanna see the output frames in a stream by replacing the previous.It is run in google colab import numpy as np import tensorflow as tf import cv2 ...
-1
votes
0answers
16 views

Finding/Closing contour that runs off image

I have an image which is the output of a Canny edge detection algorithm. The results are good, however, when it comes to finding the contours, It can't spot/close the contour, because the shape runs ...
-2
votes
0answers
39 views

Confused what is going on in python function that is running inference on webcam

I am using the object_detection_tutorial.ipynb from tensorflow. The actual tensorflow code is fine, but I am confused by some of the numpy array stuff and what is going on - especially the first 10 ...
0
votes
1answer
28 views

Relation between bounding box coordinates in object detection

In object detection, what is the difference between the set of coordinates left top right bottom and the set xmin ymin xmax ymax. Are they the same thing? If not, is it possible to convert from one ...
0
votes
0answers
9 views

TypeError: Failed to convert object of type <class 'list'> to Tensor

I am trying to train the lstm object detection on my own dataset. I have created sequence examples of 20 frames per video. The sequence features are image/encoded, bbox/xmin, bbox/xmax, bbox/ymin, ...
0
votes
0answers
18 views

How to use CNN model to detect object recognized by YOLO

Let start by saying that i have 2 pre-trained models (in hdf5 files): The first model is a YOLO-based model, trained on dataset A, which is used to locate human in any images (note that: a trained ...
0
votes
1answer
32 views

How to choose hyperparameters to train a good object detection model on AWS sagemaker?

Object detection with AWS sagemaker algorithm. I have created object detection models with and without automatic tuning. Some of them have good mAP and some don't and when I test it on new pictures, ...
1
vote
0answers
30 views

How do I train RPN in Tensorflow for faster-rcnn

I am trying to build the Faster-rcnn architecture defined here. There are three main parts, the feature extractor, region-proposal-network (rpn), and the detection/classification network. I was able ...
0
votes
0answers
63 views

Implementation and testing of wood defect detection algorithm in C#

I'm implementing knot detection algorithm wooden boards from the article: https://www.researchgate.net/publication/...
0
votes
0answers
13 views

Improving accuracy and freeze layers using Tensorflow's Object Detection API

I am using Tensorflow's Object Detection API and the ssd_mobilnet_v1_coco (it is used quite a lot in hand detection projects) trained model in a palmar hand detection project. How do I make sure it is ...
0
votes
1answer
30 views

Can we use a model trained with image classification to help in object detection in tensorflow?

I have used Tensorflow-for-poets to build an image classification model. However, I now want to use the trained model in an object detection model. Can I just import the .pb files directly or do I ...
-1
votes
1answer
38 views

Finding imagesets which are labelled for object detection? [closed]

I am building some object detectors with Tensorflow. Really enjoying it. The most time-intensive part of any project I work on is gathering images and drawing bounding boxes around the relevant ...
0
votes
0answers
14 views

Using Lidar images and Camera images to perform object detection

I obtain depth & reflectance maps from Lidar (2D images) and I have also camera images (2D images). Image have the same size. I want to use CNN to perform object detection using both images. It ...
-1
votes
0answers
22 views

How text detection in image by yolo can draw different bounding boxes on image?

I am trying to train a network to detect text in images. For training dataset, I have used the individual alphabets. If I am giving an image of that character it is perfectly showing me the bounding ...
0
votes
0answers
28 views

object detection opencv blurriness

I am new to object detection using USB webcam. I have a USB webcam which is capable of recording at 30fps FHD. I've connected this camera to a linux machine to capture video. The USB camera is ...
0
votes
0answers
10 views

Model not Predicting any bounding box

I am using tensorflow for object detection on CPU. I have tried this ssd_mobilenet_v1_coco_11_06_2017 and ssd_inception_v2_coco_2018_01_28 for training the model. The problem is after training, ...
0
votes
0answers
18 views

How do we get rid of the duplicate box in Python?

I'd like to remove the overlapping boxes from Python. like this I want to get rid of the red box coordinates here and know only the black box coordinates. Now, I'm doing it by removing it if it's ...
0
votes
1answer
20 views

Create multiple images with different ratio PyTorch

I'm trying to perform some digit recognition using PyTorch. I have implemented a convolutional version of the sliding window with size 32x32. Which makes me able to identify digits of this range of ...
0
votes
1answer
33 views

How/where the checkpoint files are loaded

I am running model_main.py of tensorflow object_detection model. I would like to know which .py file has the code, where the model checks for existing checkpoint in 'mode_dir' and how does the model ...
0
votes
1answer
22 views

Using ssd_inception_v2 to train on different resolution

The dataset contains images of different sizes. The pretrained weights are trained on 300x300 resolution. I am training on widerface dataset where objects are as small as 15x15. Q1. I want to train ...
0
votes
0answers
14 views

Train object detection with large images

Can I train the object detection model with large images size 1600*1216 and obtain good accuracy . Thanks
2
votes
2answers
49 views

How to add class to existing model?

I have trained a model using tensorflow object detection/SSD mobilenet. It works great! I'd like to add a class to it - just to detect pens or something. How can I do this? I have created my image ...