Questions tagged [object-detection]

For questions related to object detection (where objects can be e.g. humans, dogs, houses, etc.), whose meaning or definition can vary depending on the context. OD can refer to the task of locating (i.e. finding the coordinates) an object in an image (so, in this case, it would be a synonym for object localization) or the task of locating the object and classifying it (i.e. object localization + object classification).

78 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
6
votes
1answer
143 views

Extending FaceNet’s triplet loss to object recognition

FaceNet uses a novel loss metric (triplet loss) to train a model to output embeddings (128-D from the paper) such that any two faces of the same identity will have a small Euclidean distance, and such ...
5
votes
1answer
87 views

Are there any easy ways to create annotated training images for object detection?

For the purposes of object detection, are there any easy ways to create annotated training images? For example, if we have $10,000$ images and want to draw bounding boxes on 2 objects for each image, ...
4
votes
0answers
563 views

What are the differences between Yolo v1 and CenterNet?

I recently read a new paper (late 2019) about a one-shot object detector called CenterNet. Apart from this, I'm using Yolo (V3) one-shot detector, and what surprised me is the close similarity between ...
3
votes
0answers
24 views

Defect Detection System using Deep Learning

What is the general approach to defect detection in deep learning? Would the approach be better if we try to learn the positive images (defects in images) as much as possible or we try to learn the ...
3
votes
0answers
75 views

Does Retina-net's focal loss accomplish its goal?

Taking out the weighting factor we can define focal loss as $$FL(p) = -(1-p)^\gamma log(p) $$ Where $p$ is the target probability. The idea being that single stage object detectors have a huge ...
2
votes
0answers
27 views

How are nested bounding boxes handled in object detection (and in particular in the case of the SSD)?

The basic approach to non-maximum-suppression makes sense, but I am kind of confused about how you handle nested bounding boxes. Suppose you have two predicted boxes, with one completely enclosing ...
2
votes
0answers
27 views

If random rotations are included in the data augmentation process, how are the new bounding boxes calculated?

When studying bounding box-based detectors, it's not clear to me if data augmentation includes adding random rotations. If random rotations are added, how is the new bounding box calculated?
2
votes
0answers
21 views

What is the difference between text-based image retrieval and natural language object retrieval?

I'm working on creating a model that locates the object in the scene (2D image or 3D scene) using a natural language query. I came across this paper on natural language object retrieval, which ...
2
votes
0answers
90 views

Can I resize my images after labeling them?

Is it okay if I label my images with their original size and then resize them, or should I first resize them and then label them? I mean do I need to recalibrate my labels if I resized my images?
2
votes
0answers
60 views

What is a heatmap in the CornerNet paper?

I have been working on understanding how CornerNet works, but I couldn't figure out a few parts about the architecture. First, the authors mention that there are 3 distinct parts to be predicted as a ...
2
votes
0answers
28 views

Detect object in video and augment another video on top of it

I'm trying to detect an object in a video (with slight camera movement), and then augment another video on top of it. What is the simplest approach to do that? For instance, let's assume I have this ...
2
votes
0answers
30 views

Can the addition of low-quality images to the training dataset increase the network performance?

I already trained a deep neural network called YOLO (You Only Look Once) with high-quality images (1920 by 1080 pixels) for a detection task. The result for mAP and IOU were 93% and 89% respectively. ...
2
votes
0answers
39 views

What is the expected value of an IOU in this case?

I have a detection problem. An object with a probability of 0.5 is in a box with coordinates ((0,0), (2, 2)) and with a probability of 0.5 a box with coordinates ((2,0), (4,2)). What is the maximum ...
2
votes
0answers
19 views

Can an image recognition model used for human pose estimation?

I am currently writing my thesis about human pose estimation and wanted to use Google's inception network, modify it for my needs and use transfer learning to detect human key joints. I wanted to ask ...
2
votes
0answers
40 views

FasterRCNN's RPN network training

I would like to know if my understanding of RPN training is correct, and if never training the RPN on some specific anchor box is bad (i.e if the anchor never sees good nor bad examples). To make my ...
2
votes
0answers
294 views

How can I train YOLO with the COCO dataset?

I am trying to implement the original YOLO architecture for object detection, but I am using the COCO dataset. However, I am a bit confused about the image sizes of COCO. The original YOLO was trained ...
2
votes
0answers
14 views

yolo output and how to define labels for backpropogation on it

I want to build the yolo architecture in keras but can't understand the basic idea behind the training of the yolo, like how to define the labels for whether there is no object there what we have to ...
2
votes
0answers
14 views

How mAP is unfair evaluation metric for Object Detection?

The following figure is from the last page in YOLOv3 paper highlighting how mAP is unfair metric for evaluating Object Detectors: The figure shows two hypothetical Object Detector results which the ...
2
votes
0answers
49 views

How should I build an AI that quickly detects falling game assets on screen?

I want to build an AI that plays a simple android game. The game is just a one at a time object falling, some times at an angle. The AI needs to recognize the object and to decide whether to swipe ...
2
votes
0answers
26 views

How to voxelize multiple frames at the time and append them together?

I'm trying to implement this approach for object detection and tracking. In this approach, the first step is voxelize each frame to construct a 3D tensor, the second step is to append multiple voxels ...
2
votes
0answers
65 views

How to choose our data set wisely?

I have a couple of questions and I was wondering if you could answer them. I have a bunch of images of the cars, side view only. I want to train the model with those images. My objects of interest ...
2
votes
4answers
209 views

Can bounding boxes further improve the performance of a CNN classifier?

Suppose I have a standard image classification problem (i.e. CNN is shown a single image and predicts a single classification for it). If I were to use bounding boxes to surround the target image (i.e....
2
votes
2answers
60 views

Recognition of lines in a chalkboard

I'm trying to develop a real-time application that, from the sequence of chalkboard images captured by a webcam, recognizes the lines being draw on it. It must be able of recognize the lines from ...
1
vote
0answers
18 views

Object Detection as a means of Anomaly Detection

Is it possible to train an Object Detector (e.g. SSD), to detect when something is not in the image. Imagine an assembly line that transports some objects. Each object needs to have 5 screws. If the ...
1
vote
0answers
29 views

Face detection and replacement in photos

I have 2 photos, and my goal is to detect the face in one and place it on the face of the person in the other photo- basically face detection and replacement. It's not deep fakes. It's more of a ...
1
vote
0answers
23 views

How is the shape of the anchor boxes predefined in YOLO algorithm?

I am not sure if I really understand how anchor boxes are defined. As far as I understand, in YOLO algorithm you define a set of "good" shapes (anchor boxes) that may contain the object you ...
1
vote
0answers
27 views

When training deep learning models for object detection in images, do you need a large number of images, or a large number of training samples?

I am training a deep learning model for object detection. The consensus is that the more images that you have, the better the results will be. All the tutorials that I have seen say that more images ...
1
vote
0answers
12 views

Find object's location in an area using computer vision

I'm trying to see how to detect the location of a soccer ball in the field using the live camera. What are some ways to achieve this? 1- Assuming we have a fixed camera with a wide shot. How to find ...
1
vote
0answers
52 views

Getting bounding box/boundaries from segmentations in UNet Nuclei Segmentation

From my understanding, in a tissue where nuclei are present and need to be detected, we need to predict bounding boxes (either rectangular/circular or in the shape of the nucleus, i.e. as in instance ...
1
vote
0answers
22 views

Machine Learning Techniques for Objects Location/Orientation in Images

what Machine Learning tool can understand in which location and orientation a picture was taken from? That is from pictures of similar objects, say for example pictures of car interiors. So given a ...
1
vote
0answers
28 views

Keeping track of multiple faces throughout a video

I have a video where multiple persons are seated. I need to keep track of the emotions they show throughout the video. My final result should be a csv file with all the emotions depicted by each ...
1
vote
1answer
60 views

What do we mean by 'principal angle between subspaces'?

I came across the term 'principal angle between subspaces' as a tool for comparing objects in images. All material that I found on the internet seems to deal with this idea in a highly mathematical ...
1
vote
0answers
12 views

Can I train an object detection model with images with a white background?

To be more specific I have a dataset of 2400 images with unbalanced classes, 1 object per image and sometimes some objects are repeated along the dataset but in a different position and rotation of ...
1
vote
0answers
21 views

Does the selective search algorithm in object detection learn?

I am trying to get a better grasp of how object detection works. I (almost) completely understand the concept behind RPNs. However I am little bit confused with the selective search algorithm part. ...
1
vote
0answers
24 views

How come a detection works after global average pooling 2D?

I use an off-the-shelf convolutional neural network, where at the end of the convolutional part, the depth of the last convolutional layer is expanded and then its 2D average is computed (such that ...
1
vote
0answers
62 views

Dealing with very similar object classes in object detection

I'm working on an object detection problem using Faster R-CNN. I need to identify two object classes, and they are very similar to one another. Furthermore they are similar to a third type of object ...
1
vote
0answers
33 views

How to adapt MTCNN to large images with relatively small ROIs

This question could be generalised to how to adapt state-of-the-art object detection models to large images with small ROIs. In my particular case I'm trying to use this implementation of MTCNN to ...
1
vote
0answers
17 views

Irregular results while prediction identical object on same image

I used the pre-trained model faster_rcnn_resnet101_coco.config with my own dataset. I have two issues some objects were not detected, while I learned it, with a high number of steps, and test over ...
1
vote
0answers
20 views

CBIR and object detection

How does CBIR (content based image recognition) fit into the problem of object detection? Let's say we want to detect 4 types of dogs (Golden Retriever, Cocker Spaniel, Greyhound, and Labrador). We ...
1
vote
0answers
17 views

Similarity of Images (CBIR) for two different cameras

Suppose we have a top down picture of an object (let's say it is a shoe) from an overhead camera. Also suppose we have a database of various objects from a closeup camera. If we feed the top-down ...
1
vote
0answers
22 views

Post-classification after inference

I designed a fire detection using Deep Learning based classification approach. In my training dataset, I have both fire and fire smokes are supposed to be detected (all under "fire"; mostly real fires ...
1
vote
0answers
20 views

Text detection on English and Chinese language

https://arxiv.org/abs/1910.07954 In this paper, we have a convolutional character neural network where we have object detection by taking a character as a basic unit. First, we do character detection ...
1
vote
0answers
19 views

Finding unique faces in a video

I am trying to find unique (distinct) faces in multiple videos files. What is the best way to do that?
1
vote
0answers
29 views

YOLOv3 Synthetic Data Training

Suppose we want to train a model to detect various objects. Let's say we have training data of those objects in various backgrounds along with their bounding boxes. Basically these objects have been ...
1
vote
1answer
165 views

Object Detection Algorithm that detects four corners of arbitrary quadrilateral, not just perpendicular rectangular

Is there some established Object Detection algorithm that is able to detect the four corners of an arbitrary quadrilateral (x0,y0,x1,y1,x2,y2,x3,y3) as opposed to the more typical perpendicular ...
1
vote
0answers
185 views

Find the nearest object in a image which is captured from camera?

Objective : To find the nearest object (closer distance object) in the single camera image. But Image Contains multiple objects shown below: I searched in the net and found this formula to ...
1
vote
0answers
21 views

Do backgroundSubtractor functions in opencv only detect moving objects?

There are some backgroundsubtractor functions in opencv like backgroundsubtractormog2 , backgroundsubtractorGMG and ... . It seems that these functions only detect moving objects in a video. But I ...
1
vote
1answer
132 views

In Faster R-CNN, how can I get the predicted bounding box given the neural network's output?

The RPN loss in Faster RCNN paper is $$ L({p_i}, {t_i}) = \frac{1}{N_{cls}} \sum_{i} L_{cls}(p_i,p_i^*) + \lambda \frac{1}{N_{reg}} \sum_i p_i^* L_{reg}(t_i, t_i^*) $$ For regression problems, we have ...
1
vote
0answers
17 views

learning object recognition of primitive shapes through transfer learning problem

Question on transfer learning object classification (MobileNet_v2 with 75% number of parameters) with my own synthetic data: I made my own dataset of three shapes: triangles, rectangles and spheres. ...
1
vote
0answers
82 views

How to count pixels in a object mask which is segmented using Mask R-CNN?

I have segmented concrete cracks from concrete structure images using Mask R-CNN. Now I need to measure the length of the segmented masked crack. Will the pixel counting method work? Can anyone help?...