Questions tagged [object-detection]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
2
votes
0answers
14 views

What is the difference in computational cost at inference time between object detection and semantic segmentation?

I am aware that YOLO (v1-5) is a real-time object detection model with moderately good overall prediction performance. I know that UNet and variants are efficient semantic segmentation models that are ...
1
vote
0answers
15 views

Why are axes-aligned bounding boxes used in object detection

I understand (I think) why in object detection, the result is a rectangle: it is a simple shape that can be defined by 4 variables (2 pairs coords of opposite corners or 1 pair of coords + width and ...
1
vote
0answers
76 views

Yolo issue with detecting positives

I've recently tried to implement a Yolo detector for traffic light detection based on yolo v1 implementation in Tensorflow/Keras. My model really struggles with detecting small objects. Loss function ...
1
vote
1answer
15 views

Photorealistic synthetic data for object segmentation

Let's say that we have a very small labelled dataset for instance segmentation and there is a photorealistic physics engine available that can produce synthetic data for us. Looking on the web I haven'...
0
votes
0answers
18 views

Keras RetinaNet implementation and width, height order

I'm trying to use the excellent open source implementation of RetinaNet with keras (https://github.com/fizyr/keras-retinanet) and I've noticed a little detail that I would like to clarify. In the ...
0
votes
0answers
30 views

How to convert VGG VIA Instance segmentation annotation to COCO/PASCAL for Tensorflow Object Detection?

I have VGG VIA JSON annotations for instance segmentation for counting diamonds from a given image. The annotations are mixture of Circle, Polygons, Polylines. However, I am planning to use the ...
1
vote
0answers
12 views

Optimizing a model for three different metrics that have different ranges

I have a multiple object tracker that I apply on a specific object in an image series. The tracker has several parameters that can be adjusted which affects the performance of the tracking. I am ...
0
votes
1answer
45 views

What I need to write in the line level of torch.vison for 21 classes?

In this code I found , line labels = torch.ones((records.shape[0],), dtype=torch.int64) ,that there is only one class and 0 in the case of Faster RCNN is reserved for the Background. What would be ...
0
votes
0answers
6 views

Why can't SPPnet update convolutional weights according to the fast R-CNN paper?

While discussing the drawbacks of SPPnet in the fast R-CNN paper, the authors state "But unlike R-CNN, the fine-tuning algorithm proposed in [SPPnet] cannot update the convolutional layers that ...
0
votes
0answers
13 views

Understanding the training of R-CNN architecture, why is SVM necessary?

In the R-CNN paper, when referring to the training of CNN extraction module, the authors say: "Aside from replacing the CNN’s ImageNetspecific 1000-way classification layer with a randomly ...
1
vote
0answers
45 views

How much memory will be required to train EfficientDet D7 for object detection?

I am planning on doing some object detection once I collect my image database and annotate the images. I'm going to use the TensorFlow 2 detection Model Zoo, as it offers a great selection of pre-...
0
votes
0answers
19 views

Mask RCNN 1 class only

I am looking to use only one class, person (along with BG, background), for the Mask RCNN object detection. I am using this link: https://github.com/matterport/Mask_RCNN to run the mask rcnn. Is ...
2
votes
1answer
29 views

Using the whole dataset for testing (not validation) in case of small datasets

for an object detection task I created a small dataset to train an object detector. The class frequency is more or less balanced, however I defined some additional attributes with environmental ...
1
vote
0answers
73 views

Tensorflow: How to load/restore a FULL model (.pb, .pbtxt, .graph, .ckpt, variables, events)?

I recently switched from PyTorch to TF (1 and 2) and I am trying to acquire a good workflow with it. The simple things I want to do are the following: Load a full pretrained object detection model ...
1
vote
0answers
84 views

Region Proposal Network - How to subsampling 256 fg/bg anchors

I am trying to understand training process of RPN. I have problem with creating mini batches of 256 anchors. If features map has shape 18x25=450 and every position has 9 anchors it is 4050 potential ...
0
votes
0answers
15 views

Detect photos of boats which have the Europe's flag installed on it

My task is a binary classification: is there a boat in the picture that has the Europe flag installed on it? In other words, my classifier should first detect if there is a boat in the picture or not, ...
1
vote
0answers
12 views

Comparison of different ways of Upsampling in detection models

There are various ways to increase the resolution of tensor in (width, height) dimensions, frequently used in detection models like ...
0
votes
0answers
19 views

object detection algorithm for video

Is there any way to convert the detected object from an object detection algorithm (Mask RCNN in my case) to a white silhouette (while the background has been set to black)? I have commented on the ...
1
vote
0answers
33 views

Best practices to image annotation for object detection when objects overlap

If I have the following example: How should I annotate the bottom image? I can think of those scenarios: Create a large box that captures class B and a second box that captures entirely class A. ...
0
votes
0answers
12 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 ...
2
votes
2answers
46 views

“Object” Detection in Textual Data

I have a task where the input is a parsed document (i.e., full text in 1 string or tokens) and I need to classify parts of the text into say 5 classes (i.e., 5 tokens from the entire text are labeled ...
0
votes
0answers
8 views

What makes a high quality image dataset?

I am constructing a custom dataset for image classification. It is a simple task in the sense that only one class needs to be detected. However it is crucial that the dataset is high quality, and I am ...
0
votes
0answers
10 views

Evaluating the performance of tracking multiple objects detected with object detection

I have a ground truth dataset where the objects have been manually annotated and each object have been provided an ID that is consistent through time. There are no false positives or false negatives ...
0
votes
0answers
13 views

What is the best way to integrate our classes with mscoco classes?

I am using object detection api (https://github.com/tensorflow/models/tree/master/research/object_detection) with efficientdet-d0. I am interested with one class in MSCOCO (say class C), and two ...
1
vote
0answers
19 views

Pre trained vehicle detection from low altitude view

I have a very noob question. I need some solution to detect all vehicles in the video (or at least in the image). I have tried YOLOv3, however, it cannot recognize cars from the top (like that in the ...
0
votes
0answers
7 views

How do I convert image bounding boxes to SSD multi-resolution bounding box labels for training?

In SSD bounding boxes are predicted for feature maps at different resolutions. I have trouble understanding how to relate the four predicted quantities of each box detector, at different resolutions, ...
0
votes
0answers
23 views

Pretrained CNN model on animal dataset ( turtles images if exist )

I was wondering if there is a pretrained CNN model on an animal dataset. I am participating in a turtle face detection competition and was wondering if there was a pretrained image model to fine tune ...
3
votes
0answers
52 views

What are the 'protos' in TF Object Detection?

I am struggling to understand what are the 'protos' in TF Object Detection? Why do we need them here? Also, while setting up the TF API we need to download and compile protocol buffers. There is also ...
0
votes
0answers
18 views

How to feed in the bounding box annotations to MobileNet (preferably v3) for training using keras?

I am trying to train an object detection model using transfer learning with MobileNet as the base model in AWS sagemaker. (The answer doesn't have to related to sagemaker. I can manage to add it if I ...
3
votes
0answers
26 views

How to train YOLOV4?

I am going to write yolov4 real-time object detection, and I have to do it for car then vehicle plate number, but it does not have to find plate number if there is no car, first car then number on car,...
0
votes
1answer
127 views

Concept of xml files for haar cascade in object detection with opencv?

I've just started ML and since I entered a project on object detection, their haar cascade is used and XML files are loaded via OpenCV for detection. So I would like to understand why XML files are ...
1
vote
1answer
17 views

For obejct detection, should I resize my custom images first and then start the annotation or it won't matter?

I have my custom dataset images of size (1080 x 1920) and I am trying to use yolov3 for object detection. I noticed that yolov3 model accepts an input image size of 416 x 416. So I am in confusion if ...
0
votes
1answer
28 views

Cause of periodic jumps in loss function

I might be missing something obvious as I am new to machine learning. I am training an SSD Inception V2 for detecting buildings from satellite images. I use the Tensorflow Object Detection API. I am ...
0
votes
0answers
16 views

how to make the object detection detect only full object not part of it?

I have trained an object detection model to detect different kinds of cards and crop them and save them, the model detect the object very well and I got a good accuracy, now I want to add some post-...
0
votes
0answers
9 views

Creating the Yolo Training datasets from Scrapped video as training model

I have gathered the 200 car type video for one car type and model Auto detection with YOLO (Accessible by this link), and converted the video of folders to photo by this colab page shown here: So i ...
1
vote
0answers
42 views

Preprocess problem Faster RCNN in tensorflow object detection API

I've wrapped meta-architecture with the code below: ...
0
votes
2answers
29 views

Logic behind pre-trained weights and transfer learning

I am not sure about the logic behind, how pre-trained weights actually make sense and translate into a new problem. To be more specific; for example in a object detection network, how would a model's ...
0
votes
0answers
16 views

Effect of missing annotations in the ground truths on object detectors

I wanted to know whether not annotating some categories in our images, and feeding them into our neural network, would have any adverse effect on our model in detecting the desired objects. To better ...
0
votes
1answer
61 views

Can anyone recommend me a very good pre-trained model for face or head detection?

I really need to know the best pre-trained models to detect faces and/or peoples' head. Not a face recognition model, but only to classify whether an object is a person's head/face or not. I'm ...
0
votes
1answer
18 views

Object detection stops predicting well according to how I collect the images

On my problem I have to use 4k resolution (3840x2160) to record images and detect qrcodes at the same time. The images I end resizing it to 1920x1080 to save it on disk. The problem is that if I train ...
0
votes
1answer
16 views

Train a point rather than a bounding box for object detection

In the graph below, object detection is done through a point that points to the right place rather than a bounding box (e.g., using faster RCNN). What method enables to train such a point?
0
votes
0answers
32 views

tflite.runForMultipleInputsOutputs returns NaN

This is the tflite model being used This is the code to run tflite model ...
1
vote
1answer
31 views

Seeking for advice on near real time object detection for mobile (detect garbage within images)

I am trying to build a near-real time object detection model which should run on a mobile device. As I am new to this specific area of computer vision I would appreciate every advice on my current ...
0
votes
0answers
30 views

Why are CNN layers used for bounding box regression?

In object detection algorithms such as R-CNN, the position of bounding boxes is tuned using ridge regression. An example is R-CNN, appendix C. This answer also explains hoiw it is done in Fast R-CNN (...
0
votes
1answer
29 views

Feature extraction in machine learning

I am a bit confused by reading A survey on object detection in remote sensing. They state that machine learning-based object detection consists of three essential parts - feature extraction, feature ...
0
votes
0answers
14 views

How to interpret Tensorboard Values for ObjectDetection

I am training an object detection neural networt using tensorflow and the ssd mobilenetv3 model. I want to compare different training datasets. Which metric in tensorboard should I use for this? My ...
1
vote
1answer
113 views

What am I supposed to see on tensorboard images tab?

I'm training an object detection model with Tensorflow and monitor the training task with tensorboard. I was expecting in the Images tab of tensorboard that displayed images would show a bounding box (...
1
vote
0answers
27 views

Use YOLO v4 to detect smaller items than what it was trained on

What is the best way to use Yolov4 to predict smaller objects (that looks exactly the same) using a model trained on bigger objects without retraining the network? Which parameters in the config file ...
0
votes
1answer
17 views

Estimate the location of an object in a field using computer vision and math

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? At this point I'm more interested in ideas and thoughts and not ...
3
votes
0answers
82 views

Find missing object(s) in image with a priori knowledge about the missing object(s) (w.r.t base image)

Problem Statement: I am working on developing a method, or borrow/modify/combine existing ones, where given an golden image (reference or base with all expected objects to be present), it is able to ...

1
2 3 4 5 6