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
0answers
17 views

Is it possible to do object detection on an object classification dataset?

I'm new to computer vision, which I find fascinating. I wonder whether it is possible or if there has been any research into going from object recognition data to object detection. In other words, ...
3
votes
1answer
29 views

How does Mask R-CNN automatically output a different number of objects on the image?

Recently, I was reading Pytorch's official tutorial about Mask R-CNN. When I run the code on colab, it turned out that it automatically outputs a different number of channels during prediction. If the ...
-1
votes
0answers
17 views

best way to detect if a picture of an ID card has been occluded [closed]

I'm brainstorming for ideas here so I was wondering if any of you have suggestions on object occulsion for id cards(a finger blocking it or something) I have been focusing on edge detection hand ...
0
votes
0answers
11 views

How to obtain part filter anchors in DPM Detector

The DPM detector (https://cs.brown.edu/people/pfelzens/papers/lsvm-pami.pdf) uses latent-svm to train the weights of the root and part filters. During training for positive samples, it alternates ...
-1
votes
0answers
15 views

Pytorch YOLOv4 - Getting low mAP and IoU results [closed]

I am new to computer vision and object detection, and I am using YOLOv4 in Pytorch for the object detection. My end goal is to get my mAP to 60-70% and my IoU to 80-90%. I am trying to detect roadside ...
2
votes
1answer
54 views

When exactly am I overfitting — contradicting metrics

I am training an object detection machine learning pipeline. Among the many metrics provided out of the box by tensorflow object detection API, I look at total_loss and DetectionBoxes_Precision/mAP@....
4
votes
1answer
44 views

Why object detection algorithms are poor in optical character recognition?

OCR is still a very hard problem. We don't have universal powerful solutions. We use the CTC loss function An Intuitive Explanation of Connectionist Temporal Classification | Towards Data Science ...
0
votes
1answer
26 views

Object Detection: Can I modify this script to support larger images (Scaled YOLOv4)?

I am looking at training the Scaled YOLOv4 on TensorFlow 2.x, as can be found at this link. I plan to collect the imagery, annotate the objects within the image in VOC format, and then use these ...
2
votes
1answer
39 views

Viola-Jones algorithm: Haar-like features, how are the features extracted?

If I have an image like this 1 2 3 4 5 6 7 8 a b c d e f g h ... And I apply a Haar-like feature with a template ...
1
vote
0answers
13 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 ...
0
votes
1answer
56 views

How can Image Caption work?

I have two models and a file contains captions for images. The output of model 1 is .pkl files that contain the features of the images. Model 2 is the language model that will be trained with the ...
0
votes
2answers
35 views

Should I use U-net to label keys in a keyboard image?

This is a 600*800 image. Which algorithm/model should I use to get an image like the one below, in which each key is detected and labeled by a rectangle? I guess this is some kind of a segmentation ...
0
votes
1answer
15 views

Why do popular object detecting models output heatmaps instead of coordinators of object directly?

I think heatmap outputs of architectures like CenterNet, OpenPose, etc. can be changed to coordinator outputs, and loss functions like focal loss can be modified so they can deal with coordinators ...
1
vote
0answers
40 views

What are the main differences between YOLOv3 and RetinaNet object detection algorithms?

I am looking at a certain project that compares performance on a certain dataset for an object detection problem using YOLOv3 and RetinaNet (or the "SSD_ResNet50_FPN" from TF Model Zoo). ...
0
votes
0answers
18 views

Are there any faster and more efficient object tracking algorithms other than DeepSORT and centroid tracker?

Recently, I am trying some algorithm for object tracking, such as DeepSORT and centroid tracker. However, these trackers are slow to run on mobile devices, or even on a single-GPU laptop. Does anyone ...
0
votes
0answers
13 views

Instance Segmentation Using A Semantic Segmentation Map and Class-Wise Bounding Boxes

Is it possible to perform instance segmentation if you have the following: Binary Segmentation Map Bounding Boxes (with respective class) Let's say we're doing something within cellular microscopy ...
0
votes
1answer
15 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 ...
2
votes
1answer
21 views

Is there a methodology for splitting up annotated orthophotos into smaller photos that retain the original bounding boxes?

I'm trying to train an object detection algorithm (i.e. YOLOv4 Scaled, Faster R-CNN) on data taken from large orthophotos. Let's say I have one class, and I label the entire orthophoto with bounding ...
3
votes
1answer
57 views

How to treat (label and process) edge case inputs in machine learning?

In every computer vision project, I struggle with labeling guidelines for border cases. Benchmark datasets don't have this problem, because they are 'cleaned', but in real life unsure cases often ...
0
votes
0answers
33 views

Improving Mask RCNN by arbitrary scaling head input

Currently, I am looking at how Mask R-CNN works. It has a backbone, RPN, heads, etc. The backbone is used for creating the feature maps, which are then passed to the RPN to create proposals. Those ...
0
votes
0answers
34 views

How does the region proposal algorithm in R-CNN work? [duplicate]

I'm trying to understand R-CNN, but I'm a bit lost in the first stage (region proposal). Correct me if I'm wrong, but as far as I understand, there is an algorithm that proposes regions in the image ...
3
votes
0answers
21 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 ...
1
vote
0answers
42 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 ...
1
vote
0answers
39 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 ...
0
votes
0answers
14 views

Nonrealtime tracking for object detection (with or without deep features)

I've been doing a search for tracking systems based on bounding box for several days (like Sort, DeepSort, Motpy, ...). But neither is nonrealtime. My problem is based on the tracking of multiple ...
1
vote
1answer
38 views

Bounding Box Regression - An Adventure in Failure

I've solved many problems with neural networks, but rarely work with images. I have about 18 hours into creating a bounding box regression network and it continues to utterly fail. With some loss ...
1
vote
0answers
9 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 ...
0
votes
1answer
27 views

Is it possible to modify or replace the basic network of YOLO?

I have an idea to adapt YOLO algorithm to my application, the original YOLO algorithm is for image classifications, which have 24 convolutional layers with output class of 1000, is it possible to ...
0
votes
0answers
23 views

Which AI technique should I use for (key)point detection (in an image of a plantar pressure)?

I am relatively new to the field of AI. I have a problem that I would like to solve with AI, but I don't know which buzzwords I should use to search for solutions. I have a plantar pressure scan, like ...
2
votes
0answers
41 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 ...
0
votes
1answer
40 views

What ensemble methods are used in the state-of-the-art models?

What ensemble methods are used in the state-of-the-art models? When I surveyed the state-of-the-art methods of classification and detection, e.g. ImageNet, COCO, etc., I noticed that are few or even ...
0
votes
0answers
12 views

What are the best metrics for Multi-Object Tracking (MOT) evaluation and why?

I want to compare multiple computer vision Multi-Object Tracking (MOT) methods on my own dataset, so first I want to choose the best metrics for this task. I have carried out some research in ...
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
32 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 ...
0
votes
0answers
26 views

Is it possible to improve the average precision of YOLO trained on Open Images Dataset by fine-tuning it with COCO?

I consider pre-training a YOLOv5 with Google Open Images Object Detection dataset. The dataset includes general domain categories with ~15 M box samples. After the pre-training is done, I will fine-...
1
vote
1answer
51 views

How to compute dominant colors in an image?

I was trying Google Cloud's Vision API, and how the dominant colors part shows. I uploaded a sample image, and here is the results for the dominant colors. I realized it doesn't simply count pixel ...
0
votes
0answers
33 views

Object detection noise filtering

In my project, I am detecting only one class, which is "airplane", using yolov5. However, at some frames, the neural network labels some of the buildings as airplanes, which obviously are ...
3
votes
0answers
28 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?
1
vote
0answers
25 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
28 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
2answers
98 views

How to verify classification model trained on classification dataset on a detection dataset for classification purpose?

I am working on a problem that involves two tasks - detection and classification. There is no single dataset for both tasks. I am training two models, separate on detection dataset and another on ...
0
votes
1answer
34 views

Will changing the dimension reduction size of a neural network (i.e. SSD ResNet-50) change the overall outcome and accuracy of the model?

I am training a convolutional neural network to detect objects (weeds amongst crops, in my case) using TensorFlow. The original dimensions of the raw training photos are 4000 x 3000 pixels, which must ...
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
2answers
41 views

Get object's orientation or angle after object detection

I'm trying to get a detected car's orientation when object detection is applied. For instance, when we apply object detection on a car and get a bounding box, is there any ways or methods to calculate ...
1
vote
1answer
57 views

Why do we resize images before using them for object detection?

In object detection, we can resize images by keeping the ratio the same as the original image, which is often known as "letterbox" resize. My questions are Why do we need to resize images? ...
1
vote
0answers
175 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 ...
0
votes
0answers
38 views

Which is more accurate between HRnet-w48 and HigherHRnet-w48 for single person pose estimation?

When I started to look into the deep High-Resolution Net paper, I came to know about the HigherHRNet and the Bottom Up HRNet as well. But I can't find any metrics or proof on which is better for a ...
0
votes
0answers
31 views

Training Object Detection model on just 10 images

I am trying to train an object detection model using Mask-RCNN with Resnet50 as backbone. I am using the pre-trained models from PyTorch's Torchvision library. I have only 10 images that I can use to ...
1
vote
1answer
76 views

How can I determine whether a video's frame is realistic (was recorded by a camera) or contains computer-generated graphics?

Given a video, I'm trying to classify whether it is a graphical (computer-generated) or realistic scene. For instance, if it contains computer-generated graphics, credit, moving bugs, blue screen, etc....
1
vote
1answer
40 views

Are there any known models/techniques to determine whether a person in a store is a customer or a store representative?

Are there any known models/techniques to determine whether a person in a store is a customer or a store representative? For example, customer representatives can wear uniforms and then one possible ...