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).

109 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
11 votes
0 answers
394 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 ...
rossignol's user avatar
  • 111
6 votes
0 answers
147 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, ...
James's user avatar
  • 71
3 votes
0 answers
63 views

How are Ground truth provided to each Pyramid map in RetinaNet or YOLOv3 Paper? How is the mapping of Feature Pyramids done to Ground Truth

SO the YOLO V3 and RetinaNet both uses the Feature pyramids which look something like this: (except b and e which have one ...
Deshwal's user avatar
  • 253
3 votes
0 answers
44 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?
FourierFlux's user avatar
3 votes
0 answers
32 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 ...
user1538798's user avatar
3 votes
0 answers
118 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 ...
mshlis's user avatar
  • 2,359
2 votes
0 answers
102 views

What would be a reasonable option for clustering for unknown number of clusters and a lot of outliers?

I am implementing the CV detection pipeline with the use of SIFT and KNN Matcher. Image keypoints matched to the query keypoints produce the following image: The matched objects have a lot of key ...
spiridon_the_sun_rotator's user avatar
2 votes
0 answers
48 views

Can a GIoU loss (generalized intersection over union) be used after an STN module (spatial transformer network)?

I have a model that uses an STN module for number detection and Mean Squared Error loss. But I would like to replace it for GIoU, because MSE doesn't take into account how much of the target area has ...
Manveru's user avatar
  • 221
2 votes
0 answers
72 views

Which method can accurately detect circular/angular shapes? (attached example)

Is there a method to detect shapes like these accurately and efficiently? I have tried the OpenCv Haar Casacade Classifier which does not work well. These shapes should all be the same class object ...
Boyd Werkman's user avatar
2 votes
0 answers
100 views

Vector input to CNN for object detection

I am training a 3D object detection network (Retinanet-based as of the moment) for re-detecting tracked objects. I would like to be able to add the velocity vector of the tracked object as an input to ...
DerekG's user avatar
  • 121
2 votes
0 answers
261 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 ...
FourierFlux's user avatar
2 votes
0 answers
565 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 ...
Prasanjit Rath's user avatar
2 votes
0 answers
89 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 ...
Sid's user avatar
  • 21
2 votes
0 answers
40 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 ...
Tina J's user avatar
  • 973
2 votes
0 answers
40 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. ...
natan's user avatar
  • 21
2 votes
0 answers
391 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 ...
Alexander Soare's user avatar
2 votes
0 answers
137 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 ...
Paltusok's user avatar
2 votes
0 answers
25 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 ...
V.Hunon's user avatar
  • 131
2 votes
0 answers
48 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 ...
Michael Heidelberg's user avatar
2 votes
0 answers
740 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 ...
depressedminkycoder's user avatar
2 votes
0 answers
29 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 ...
Yash 's user avatar
  • 21
2 votes
0 answers
23 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 ...
Hesham Eraqi's user avatar
2 votes
0 answers
59 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 ...
roydouek's user avatar
2 votes
0 answers
28 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 ...
OneManArmy's user avatar
2 votes
0 answers
67 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 ...
nikki2's user avatar
  • 229
2 votes
3 answers
634 views

Face liveness detection using face landmark points

How to detect liveness of face using face landmark points? I am getting face landmarks from android camera frames. And I want to detect liveness using these landmark points. How to tell if a human ...
InfinityAndBeyond's user avatar
2 votes
2 answers
127 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 ...
pasaba por aqui's user avatar
1 vote
0 answers
11 views

Filter in the Single Shot Detector

Let's say I want to implement a single shot detector. When I get a feature mal as an input, I will use a 3x3 filter for prediction for each cell. Let's say we have 5 classes with 6 ancors, I would ...
Hans Mustermann's user avatar
1 vote
0 answers
18 views

Pedestrian/Object detection

Today automobiles have many kinds of detection systems and I'm currently researching one on Pedestrian Detection systems. I haven't figured exactly out the difference between these three systems. If ...
wtknow's user avatar
  • 11
1 vote
1 answer
43 views

NN Architecture for the detection of "sparse" Objects

I have a document digitalization task where I want to detect technical drawings from images. These Images mostly consist of objects made up of combination of shapes like lines, circles and rectangles. ...
Julian's user avatar
  • 111
1 vote
0 answers
55 views

Training with extremely imbalanced Dataset

I have a object detection problem which has extremely imbalanced dataset. Lets say there is only one class to detect, say apple or not apple. This detection network will be used in a real case ...
Uce's user avatar
  • 11
1 vote
1 answer
1k views

How does YOLO detect the object when the object is in multiple grid cells?

I have been reading various articles and watching videos on YouTube, but I can't seem to understand one thing. How does YOLO make a bounding box for an object if it is in multiple grid cells? For ...
Sharjeel M. Rajput's user avatar
1 vote
0 answers
670 views

Question about true positive and false positive detections in object detection

I am computing true positives, false positives, and false negatives in order to calculate my model's precision and recall. I am using YOLOv5. According to this source and this one, an IoU overlap ...
ihb's user avatar
  • 129
1 vote
1 answer
379 views

Mask R-CNN: How are the computed masks projected back to the input image?

The computed masks by Mask R-CNN are of fixed size $m \times m$ each. How are they projected back to the image?
orbit's user avatar
  • 21
1 vote
0 answers
133 views

Why are the learned offsets of anchor boxes in the RCNN object detection models scale invariant?

In the original RCNN paper (https://arxiv.org/pdf/1311.2524.pdf) and continued in later RCNN papers such as faster RCNN (https://arxiv.org/pdf/1506.01497.pdf) the learned offsets of the anchor boxes ...
phil's user avatar
  • 143
1 vote
2 answers
208 views

What kind of algorithm or approach can I use to find a specific type of object in an image?

What kind of algorithm or approach can I use to find a specific type of object in an image? In particular, I am interested in finding an object like a windmill in an image taken, for example, from ...
S E's user avatar
  • 111
1 vote
0 answers
42 views

In anchor based object detection, why don't the anchors share the same weights?

After reading about YOLO V3 and Faster R-CNN, I don't understand why the weights for the regression head aren't the same across all boxes of the same size. Given that the backbone of these systems is ...
FourierFlux's user avatar
1 vote
1 answer
261 views

Role of confidence or classification score in object detection mAP metrics

I know that mAP (mean Average Precision) is the common evaluation metric for the object detection tasks. It uses IoU (Intersection over Union) threshold such as [email protected] to evaluate whether the ...
Naufal Suryanto's user avatar
1 vote
0 answers
33 views

Advice required for identifying bone fragments in CT-scans using STL Files (3D image segmentation)

I am working on a project related to automating the procedure of manually segmenting some bones in CT scans and hopefully if everything goes alright in this stage, move on to do something more with ...
panda_the_great's user avatar
1 vote
1 answer
114 views

What are the state-of-the-art Person-Detektion / Human-Segmentation?

I would like to use a deep learning approach to detect people in videos. I have found some freely accessible implementations like Human Segementation with Pytorch or BodyPix / DeepLab / Pixellib with ...
miimi's user avatar
  • 11
1 vote
0 answers
287 views

Object detection approaches without anchors and NMS

The Context From all of the problems I have worked with in computer vision, the most challenging one is the object detection. This is not because the problem itself is complex to understand or bad ...
JVGD's user avatar
  • 1,108
1 vote
0 answers
127 views

Can object detection approaches be used to solve text/detection problems?

I have been working on text detection and recognition for almost two months and new on this field. So far, I have fine-tuned, tested, and trained several text detection/recognition methods, such as ...
yakhyo's user avatar
  • 154
1 vote
0 answers
13 views

Aggregating 2D object detections into 3D object detections

I have a data set of 3D images with some bounding box annotations. The images are too large to train something like YOLO 3D (would run out of memory), so I instead created slices of the 3D images with ...
deeplearningmaniac's user avatar
1 vote
0 answers
138 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 ...
oezguensi's user avatar
  • 205
1 vote
0 answers
60 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 ...
Tina J's user avatar
  • 973
1 vote
0 answers
37 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 ...
IgnacioGaBo's user avatar
1 vote
0 answers
51 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 ...
ihb's user avatar
  • 129
1 vote
0 answers
130 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 ...
Tina J's user avatar
  • 973
1 vote
0 answers
63 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 ...
user3755529's user avatar
1 vote
0 answers
1k 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?
Ali Khalili's user avatar