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).

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

YoloV5 Calibration

I'm currently tackling the task of calibrating object detection models specifically tailored for medical imaging applications. Despite extensive online research, I've encountered difficulties in ...
Kanan Suleyman's user avatar
0 votes
0 answers
7 views

Yolo object detection metrics

I have made some predictions and saved the results to YOLO format. Then I made a program to calculate metrics, every metric looks fine except Precision/Confidence curve. I guess the flatline at the ...
Andrés Rodríguez Lorenzo's user avatar
0 votes
0 answers
54 views

Model architecture object detection where entire image context and nearby objects are important to accurate prediction

I'm working on a model to classify multiple extremely similar looking objects in a single image. A simple object detection model works ok but the issue is that I'm classifying similar looking object ...
Will's user avatar
  • 101
0 votes
1 answer
66 views

Why YOLOv7 not detecting small objects

I am using YOLOv7 trained on custom dataset, and using the model weights after converting to ONNX for CVAT annotation. There it's only predicting few small objects. Is there any limit on small object ...
bibinwilson's user avatar
0 votes
0 answers
55 views

Use AI/Computer Vision to detect scene changes

I'm trying to use AI and computer vision techniques to identify scene changes for a camera. Something like this: What are some approaches to do this? Any ideas? The scene is static. Somewhere I saw a ...
Tina J's user avatar
  • 973
0 votes
0 answers
12 views

Meaning of Objective and Risk in DLIB HOG-SVM detector

I am using dlib simple object detector for training a HOG-SVM object detector. Everything is working fine when I test manually. However, I can't find any resources that tell me what is the meaning of ...
lonewolf.py's user avatar
0 votes
0 answers
9 views

Are image classification nets independent of input size ? Which ones?

Most models I have seen have a dense layer at the exit of the network with a softmax function or a relu sometimes, so I thought this was confusing: The major hurdle for going from image ...
Minsky's user avatar
  • 101
0 votes
0 answers
14 views

Recognize Logos and their Sources

I am working on a problem where I have to recognize logos and also output about the logo placement (logo source). I have attached an image below for visuals, if any of the logos on the below image is ...
HKay's user avatar
  • 101
0 votes
1 answer
87 views

Can DeepSort be made to track objects beside people?

As far as my understanding goes, the model used for feature extraction in DeepSort is specified as the first argument of the function create_box_encoder in the file ...
Mehdi Charife's user avatar
0 votes
1 answer
170 views

Is it effective to use images without objects in object detection?

I am currently using faster_rcnn to train a set of images with only one category, in fact, there are only good images and images with defect in the whole dataset,and I use roboflow to labeling this ...
Kekai's user avatar
  • 3
0 votes
0 answers
62 views

Image Alignment/Homography of Subject in Bounding Box

I've been trying to design an algorithm for aligning an object across two photos in realtime. I am able to localize the object (create an ROI/BBox) through an object detection (siamese) network for ...
FrederickGeek8's user avatar
1 vote
1 answer
193 views

How can I limit the number of things Yolov7 can Identify?

So Yolov7/v8 are able to classify numerous distinct objects. One of those objects is cups for example. If I wanted to only look of cups how would I change my setup without having to do custom object ...
Drew Patton's user avatar
0 votes
0 answers
286 views

How to extract the high-level features of YOLOv5?

I am faimilar with extracting the high-level features from any pretrained model for classification problem such as ResNet version, VGG, etc. It is easy to extract the features because there is a fully ...
Hamzah's user avatar
  • 103
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
14 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
0 votes
0 answers
63 views

Help on Object-Detection Task - Detection of Cracks on Walls (Pre-Trained Models etc.)

I'm member of a University Project Team in D.U.Th., a university in Greece. Lately, we have been trying to implement a Neural Network Model for our Project and, so far, we have had some progress worth ...
Eliasmys's user avatar
0 votes
1 answer
80 views

How vision models based on CNNs learn the relative positions of each pixel in the image?

A CNN model is based on a series of filters applied to an image. However, these filters can only "see" a small portion of the image and they have no information of the relative position of ...
IgnacioGaBo's user avatar
0 votes
0 answers
12 views

Best approach for object detection with a small dataset and large shape variation

I want to train an object detection model to detect an object of interest. I have about 400 annotated images taken by a fisheye camera from different positions, orientations and distances, and a ...
firion's user avatar
  • 269
0 votes
1 answer
104 views

Keypoint generation in 3D point clouds with Deep Learning

I have a huge dataset of 3D point clouds (each point consists of X,Y,Z coordinates) and another dataset with keypoints (also X,Y,Z) which lie on quite recognizable structures in the point cloud. As a ...
nmb's user avatar
  • 1
0 votes
0 answers
31 views

What computer vision techniques can help me select the best image for object detection inference?

I have a lot of duplicate images. I need to make a selection to reduce the amount of images the Mask RCNN model will perform inference on. In every collection of duplicates, the images slightly differ....
Nick De Wispelaere's user avatar
0 votes
0 answers
133 views

How to balance classes for YOLO?

The problem I am having is that to my understanding we need to annotate all objects of all classes on the images we want to train (or fine tune) our YOLO on. This is because YOLO compares labeled ...
GKozinski's user avatar
  • 1,240
1 vote
1 answer
234 views

Does object detection for single-class images have any advantages over classification?

I recently joined a new project, and saw that they are using object detection instead of image classification for one of the business cases. The images can only belong to one class (example, the image ...
user27771's user avatar
1 vote
1 answer
81 views

How to ensure continuity of AI model logic?

I am aware that this question might be vague but I must try anyways. I am looking for a method or an algorithm or even just some keywords (to conduct further research) of how to deal with phenomenon ...
GKozinski's user avatar
  • 1,240
1 vote
1 answer
35 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
0 votes
0 answers
19 views

Are there computer vision models that can learn long range dependencies on features outside bounding box of an object in an image?

I am trying to solve a problem that has to do with extracting the major vitals from an ICU monitor, that includes HR, RR, Sys-Dia, MAP etc. (The large numbers on the screen as a crude rule). The ...
Aditya Prakash's user avatar
0 votes
0 answers
375 views

YOLOv7 fine tuning with unbalanced dataset

I have a question about training object detection models especially using the YOLOv7 algorithm. I use a Soccer Players Dataset from the Roboflow. The dataset is very unbalanced. I trained the model ...
ofevy's user avatar
  • 1
0 votes
0 answers
70 views

Yolov7 change area of detection

I'm using yolo to detect cars that enter my street. I recently ordered a new camera to upgrade my setup. But i didn't thaught about the fact that higher resolution meant lower performance. And ...
mxsmohT's user avatar
0 votes
2 answers
142 views

Can object detection algorithms distinguish a same object as different classes only based on different surroundings?

I am doing an experiment. The following image is an example of the annotation I do. There are 2 classes: 1) sun, 2) moon. Red boundary box labels the moon, and the green boundary box labels the sun. I ...
Raymond Pang's user avatar
0 votes
1 answer
794 views

Split dataset into Train/Validation/Test for Object Detection

I have a dataset for Object Detection with YOLO format labels, each imagine can have occurences of different classes and multiple occurences of the same class. How can the dataset be divided into ...
1stTimeStackOverflow's user avatar
0 votes
0 answers
92 views

How to handle multiple object instances in object detection?

I’m constructing a neural net with Keras for object detection for identifying hamburgers. I have a data set with the objects and each image has an array of bounding boxes (there are between 1 and 5 ...
C.J. Windisch's user avatar
0 votes
0 answers
48 views

How to keep the best shot of an object with an Object detection model over a video

I’m pretty new to Machine learning and stuff. I’m going to start to work on a project, I have a background with code. My goal is to collect data from my city roads and build a strong dataset for ...
mxsmohT's user avatar
0 votes
1 answer
135 views

Detecting object position given the relative position of another object

I know that the title might be redundant but I'm trying to understand if there is way to predict where a specific object will be if I provide a certain object as a reference. See as an example the ...
Diauro's user avatar
  • 1
-1 votes
1 answer
82 views

Why do we need Tensorflow, Keras and other ML/AI modules?

This question might seem stupid at first glance, and it might be - that is because I am very new here and I've tried to think about an answer of my own, and search this question but to find no answer.....
JetLeg's user avatar
  • 1
1 vote
1 answer
93 views

Survey on non-machine learning object detection algorithms

I am working on a project in which I will be performing object detection on deformed objects. Unfortunately, there isn't enough data sets to train them on some neural network. I am looking for ...
UserX's user avatar
  • 13
0 votes
0 answers
22 views

Can NotA (none of the above) class be combined with object detection / segmentation models?

So there's this way of classifying an object as NotA (none of the above) class as described in https://arxiv.org/abs/1910.02830 So mostly this uses a sort of confidence thresholding with different ...
MachineLearner's user avatar
0 votes
1 answer
292 views

How do I train a model to classify if it's a Full Human Body in the picture?

recently I started a personal project that uses some Machine Learning techniques in the process, so I'm currently collecting human images with a web scraper. I know that I can use some pre-trained ...
Igor Michetti's user avatar
0 votes
2 answers
68 views

How to measure classification accuracy in object detection task?

Object detection uses mAP as the metrics. But if we are only interested in classification once the object in a bounding box is extracted, what metrics should we use? Thanks!
Curimeow Cat's user avatar
0 votes
2 answers
488 views

Using pre-trained models on image dataset that is totally different for object detection?

I have been trying out various tutorials on object detection machine learning. All the tutorials so far have been to use a pre-trained model for practical reasons when detecting objects that the pre-...
SunnyBoiz's user avatar
  • 103
0 votes
0 answers
30 views

Object detection on UAV images

So, the idea is that I have a custom set of UAV images. I zoomed them and I used LabelImg in order to draw the rectangles. I trained the model and when I run the code for object detection it does ...
just_learning's user avatar
1 vote
0 answers
50 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
0 votes
1 answer
29 views

Why instance segmentation architectures using reconstruction masks but not regression?

I'm wondering why many model architectures use binary mask reconstruction for segmentational CNNs, and not regression of mask polygon coordinates? Many object detectors use regression to find ...
Dmitry  Sokolov's user avatar
0 votes
0 answers
61 views

What is single object localization?

Object detection is said to be combination of object localization and image classification. However, when reviewing localization, I often come across the term "single-object" localization, ...
akastack's user avatar
0 votes
0 answers
131 views

What object detection algorithm is the best for my particular problem?

I am trying to write a program to put a bounding box around dead fish, and not the live ones, in a video. I have minimal data (~5k frames and ~7k objects in total ) and it is VERY low quality (poor ...
user avatar
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.'s user avatar
1 vote
1 answer
44 views

Deep Learning for occlusion recognition is 2D or 3D space [closed]

Given a dataset of spatial 2D or 3D object map with their bounding box annotations, How feasible would it be to train a deep learning model to recognize (classify) "occluded" objects from a ...
fhm's user avatar
  • 11
-1 votes
1 answer
542 views

Extract person silhouette from photo or video

Are there any programming libraries or neural network design patterns designed for the task of finding persons in a photo/video and extracting their silhouettes (i.e. not only the rectangle containing ...
jaboja's user avatar
  • 101
0 votes
1 answer
72 views

Is there way to segment an image without labeling/classification, as well as supervised learning?

Is there way to segment an image without labeling/classification, as well as supervised learning? For an illustrative example, if one considers an image with a dog and a cup (we don't particularly ...
Astraeus's user avatar
0 votes
1 answer
327 views

Object Classification: How to decide which detected region is a RoI for classification?

I am working on a project where I am working on the Flickr-47 dataset to do logo detection and classification. My approach is to first finetune a YOLO v5 model with high recall to detect as many "...
Kunj Mehta's user avatar
0 votes
1 answer
658 views

For an image (of any object), how to find its location in the other image(s) which contains it, given there are no labels or annotations for any image

Problem Statement: I am given 2 sets of images. All the images in both sets are without annotations and labels. First set : a set of images of the grocery store shelves (captured in the grocery stores)...
Aarush Aggarwal's user avatar
0 votes
2 answers
66 views

Performance of augmented dataset with or without original images

I am training on yolo and I had a small dataset. I decided to increase it by augmenting it with rotation, shearing, etc to increase the size and increase accuracy. Now I have seen augmented datasets ...
devman3211's user avatar

1
2 3 4 5