Questions tagged [object-detection]

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

Filter by
Sorted by
Tagged with
0
votes
0answers
18 views

Is object detection the right approach for this problem

I'm trying to build a model which, given a picture of someone's face, is able to identify all the following features, as well as others. The model would output, for each picture, a list of all the ...
0
votes
1answer
16 views

On which dataset evaluate an object detection model ? Similar or real life data?

I'm training an object detection model (SSD300) to detect and classify body poses in thermal images. Even I have more than 2k different poses, but the background does not change much (I have only 5 ...
2
votes
1answer
37 views

What is the most comprehensive overview of methods that explain why an object detection network got a particular answer?

There are methods like Grad-CAM. With them, you can look at a particular layer of the network and see how it activated for a specific input. My question is about the methods with the purpose ...
0
votes
0answers
11 views

How to find binary image's object size like objects height,width,midpoint using python?

if you see the attached two pictures,then in "the mask" section you can see 2 binary images where white background are 0 and black marked area of object is full of values with 1 now given images like ...
0
votes
0answers
17 views

Yolov3: Single-class vs multiple class

I'm really new to object detection with Yolov3. Let's say I have 10 classes and the amount of data is approximately the same. Do I achieve better average precision when I use 10 Yolo models and train ...
2
votes
1answer
28 views

Is the following considered an image classification or an object detection problem?

I've been assigned with the task of creating a model to detect whether and advertisement exists in an image and optionally to draw a bounding box around it. My first thought was that this is an ...
0
votes
0answers
9 views

How should I find similarities between individuals with multiple measures per individual?

I want to identify individual monkeys from a camera trap survey. From my accumulated camera trap videos, I see some variation in tail tuft size that I think could help me identify monkeys. I took ...
0
votes
0answers
18 views

Retraining of object detection CNN

I am working on an object detection system that should detect UI elements (such as button, checkbox, radio button, etc..) in the photo of a touch screen of printer (not screenshots, but literally a ...
0
votes
0answers
53 views

What happens if I use categorical cross-entropy for one class detection [closed]

I have used categorical cross-entropy instead of binary cross-entropy for one class detection. If the results are wrong, does the proportion maintain? Like, the worst result that I got is still the ...
1
vote
1answer
23 views

Performance of MaskRCNN/YOLO as a function of object size in pixels

I am trying to find references on how the resolution of an object affects the ability of object detection systems such as MaskRCNN and YOLO to correctly identify the object. For example, if the ...
0
votes
0answers
17 views

Evaluate precision and recall results

The following table shows the precision and recall values I obtained for three object detection models. I evaluate the first two models as the following. The target is to find the best object ...
0
votes
0answers
13 views

Can we calculate mean recall and precision

I'm evaluating the accuracy in detecting objects for my image data set using three deep learning algorithms. I have selected a sample of 30 images. To measure the accuracy, I manually count the number ...
1
vote
0answers
28 views

Sample size for the evaluation of Deep Learning Models

I'm evaluating the performance and accuracy in detecting objects for my data set using three deep learning algorithms. In total there are 24,085 images. I measure the performance in terms of time ...
2
votes
1answer
70 views

What would be the ideal dataset to train a model to detect advertisements in an image?

I am thinking of the requirements for training a model that would be able to detect if there is any kind of ad in an image. I know that this sound too broad not just for a question on CV but for ...
0
votes
0answers
17 views

object detection loss

I have trained an ssd detector in my own dataset and the values of train loss and val loss are shown in the picture. However in all the epochs the value of val loss is lower than that of train loss ? ...
0
votes
0answers
38 views

What is the purpose of grids in YOLO?

Considering the YOLO algorithm. Assume: Input image is n x n x 3 Number of anchor boxes is m For each anchor box, we have 1 (pc = probability of object) + 4 (4 variables to predict the bounding ...
1
vote
0answers
10 views

Incremental Training of object detection models

I currently have an object detection model which is deployed and working. But my client expects to have more variants of the input images, which may be ideally added to the training base and new ...
0
votes
1answer
37 views

Object detection : Multimodal or single input ? for Depth + Thermal images

I need to detect persons in a scene. I have a 16 bits depth image of that scene (640, 480) I have a 16 bits thermal image (80, 60) of the same scene (slighly different point of view) I resize these ...
0
votes
0answers
20 views

How exactly the midpoint of the object is selected in YOLO algorithm?

The boundaries of the object are encoded into 4 scalars: Bx, By, Bh, Bw. Bh and Bw are calculated using the ratio of the width of the bounding box to the width of the relative grid cell. But I can't ...
0
votes
1answer
65 views

How to calculate precision and recall with only one object class?

I have an object detection problem with only one object class. I want to compare the results and thought about using precision and recall. They are defined as follows: $$precision = \frac{TP}{TP + FP} ...
1
vote
1answer
32 views

Object detection with just one image? [duplicate]

Deep neural networks require lots of examples to learn tasks like image classification, and object recognition. On the other hand, we humans can learn and identify object just by looking at it once. ...
0
votes
0answers
194 views

Change hyperparameter of YOLOv3 for face detection

I have tried with some github implementation on YOLOv3 in tensorflow. I trained yolov3 for faces with WIDER face dataset, I haven't changed the original configuration of YOLOv3. After training the ...
0
votes
0answers
33 views

Average precision biased in object detection when validation set has easy examples

I am computing average precision (AP) for object detection as in Pascal VOC dataset. Sometimes my results were too good to be true and I suspected that I might overlook something. Then I realised that ...
0
votes
0answers
16 views

Impact of increasing number of classes on object detection rate/speed

I am trying to build a Darknet (C++) model to detect custom objects. Initially, in the testing phase for 50 objects with tiny yolo, I am getting 35 FPS speed. If I increase the number of objects to ...
0
votes
1answer
50 views

Is it possible to train a model to detect a shape? [closed]

We have multiple object detection APIs that can help us to find the bounding box coordinates. But is it possible to go a little further and find/separate the shape of the object (say cat/dog/human) ...
0
votes
0answers
137 views

Why using mAP (mean Average Precision) instead directly computing AP (Average Precision)

Problem mAP is a metric frequently used in tasks involving ranking. One application of mAP is in object detection, where for each category The predicted bounding box is organized in decreasing order ...
1
vote
1answer
45 views

Why do CNNs work on regression problems such as finding bounding boxes in images?

My understanding is that each layer in a CNN computers specific features, depending on the type of filter that has been trained, like edges/nodes/patterns etc. I can understand how this can be used in ...
0
votes
1answer
22 views

Cannot overfit Mobilenet with one example

I am trying to do a single object detection. Since the problem is much simpler than multibox object localization I decided to try using a simple CNN that predicts the object class and its location. ...
1
vote
0answers
19 views

Object detection without bounding boxes

I'm trying to think of an architecture to perform object detection from labelled images (according to object class) but any information in the labels with respect to object location. I thought I could ...
0
votes
1answer
86 views

Object distortion after ROI Align in Mask R-CNN

In Mask R-CNN, if there are 2 proposed ROIs which cover 2 objects that looks like below: #1 A square object #2 A rectangular object So my question is: After ROI Align, is the #2 feature map ...
3
votes
1answer
121 views

Training an Object Detection Model Using with Artificial Data from Video Games

I had an interesting idea of using artificial data gathered from screen shots of a high-resolution video game as a cheap substitute for labeled real data, which can be quite expensive or difficult to ...
0
votes
0answers
61 views

Training data for extracted license plates from car images

I am working on a project which uses machine learning and image processing techniques to detect/extract license plates of a vehicle given an image. In my module for data preparation and feature ...
0
votes
0answers
57 views

What YOLO architecture should I use for handwriting detection?

I want to create a cnn to draw bounding boxes around individual handwritten words. Ideally I would input a picture of a filled piece of notebook paper and get a cropped image of each word (they don't ...
0
votes
0answers
61 views

finding Human dimensions from photos

I'm working on a problem where I have to extract different human parts real-world dimensions ( waist width, arm length ) from photos where there are front and side photos, the given values are the ...
0
votes
1answer
55 views

ML model for text detection similar to object detection?

I'm n00b to ML and am looking for a text detection model which could tell me a box of pixels has X% possibility to be a word ABC, very similar to common object detection models like these. I searched ...
0
votes
0answers
51 views

When should I stop the object detection model training while mAP are not stable?

I am re-training the SSD MobileNet with 900 images from the Berkeley Deep Drive dataset, and eval towards 100 images from that dataset. The problem is that after ...
0
votes
0answers
163 views

Hough Circle vs CNN object detection

Suppose I have a dataset that contains images like this: Each picture can have between 0 to 5 ellipses. The model has to count the number of ellipses in each test image. I would like to know what is ...
2
votes
2answers
346 views

Object detection : is deep learning the only way to go?

It seems that deep learning based approaches are currently more superior to the more "traditional" methods in the domain of object detection. Methods like YOLO, for example, seem to be doing something ...
0
votes
0answers
25 views

Which model should I choose for object detection and classification

My use case is to detect the defects in vegetables in an isolated system with high accuracy and speed. Currently, I'm using Tensorflow Object Detection API (Faster RCNN) for this purpose. But I've ...
0
votes
0answers
4 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
43 views

What Neural network approach would be best suited to do loose object detection?

The example is as follows, given an aerial photo of a small section of land ( from google maps ), i want to see if my hand draw sub section of this piece of land can be detected. For example, the ...
1
vote
1answer
43 views

Does a CNN object detector always return the same results for the same image?

There're many object detectors which use convolutional neural networks to detect objects in images or point clouds, like YOLO, SSD, AVOD. My question is, if i feed the same image to an object ...
2
votes
0answers
129 views

How to reduce impact of false positive images in Tensorflow Object Detection Framework?

I am training a single object detector(for car) with Faster R-CNN with Inception v2 config file. I started with around 300 examples of images of the object with bounding boxes and trained that, got ...
1
vote
0answers
370 views

Many false positives in a custom SSD model with Tensorflow object detection API

My model has 2 classes (no background class) and is trained using transfer learning with ssd_mobilenet_v2_coco. It detects and classifies well the objects it was trained on. However, on new images it ...
0
votes
1answer
15 views

IOU vs ROBIN metrics

Came across this paper on ROBIN evaluation metrics. The metrics seem to be more informative than just IOU, so is there a reason why IOU is the preferred metric in most cases for object detection. ...
1
vote
2answers
848 views

How are YOLO anchor boxes generated?

I am recently trying out darkflow, a Tensorflow implementation of Darknet written by Joseph Redmon. Looking at the configuration files, I noticed a section called region as shown below. ...
1
vote
1answer
310 views

How best to combine object detection and tracking

I am trying to make a computer vision system which will be able to detect and track objects of interest. This will require (1) detection functionality to notice the object when it appears (2) ...
1
vote
0answers
161 views

The reason for multiple bounding boxes use for each grid cell - YOLO

I'm not quite sure what is the main reason why YOLO uses multiple bounding boxes for a grid cell. An answer I can find on web is for multiple aspect ratio in the prediction. However I don’t think it’s ...
4
votes
2answers
333 views

What is sigma function in the YOLO object detector?

I have gone through the YOLO9000 paper, in that they have mentioned that network predicts 5 coordinates of the bounding box, and from that we find the exact centre coordinates and the width and height....
0
votes
0answers
153 views

What is scale-invariance and log-space translations of a bounding box?

In slow R-CNN paper, the bounding box regression's goal is to learn a transformation that maps a proposed bounding box P to a ground-truth box G and we parameterize the transformation in terms of four ...