Questions tagged [object-detection]

For questions related to object detection (which includes e.g. human or face detection), whose goal is to locate a specific object in an image. Object detection is different from object recognition, whose goal is to find the type of object(s) in the image.

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

Which metrics of COCO API are suitable for object detection

These days I train a person detector and I use COCO API to evaluate my model. It uses Recall and Precision to evaluate a detection task. It's output is something like this: ...
1
vote
0answers
7 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 ...
0
votes
0answers
7 views

How is Average Recall (AR) calculated for an object detection model?

After looking around the internet (including this paper, I cannot seem to find a satisfactory explanation of the Average Recall (AR) metric. On the COCO website, it describes AR as: "the maximum ...
0
votes
0answers
9 views

what is the best dataset (or combination of datasets) for training a person detector?

I want to train a person detector for MOTChallenge dataset, but I want to avoid using the dataset as training set for my detector. Therefore, I want to use another dataset or combination of several ...
0
votes
0answers
6 views

Object detector always predict high confidence bounding box after dataset augmentation

I am using the Object Detection API to train a MobilenetV2-SSD object detector with just one class. I started from the sample pipeline tuned for the COCO dataset. During the first training I could ...
0
votes
1answer
64 views

Should I use single or double view for gender recognition?

My project requires gender recognition of people shown on the given images, with more than one person per image. However, these people can be positioned in frontal or side view(passing by ...
4
votes
0answers
22 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 ...
2
votes
1answer
46 views

Why tf object detection api needs so few pictures?

I am wondering why tf object detection api needs so few picture samples for training while regular cnns needs many more? What I read in tutorials is that tf object detection api needs around 100-500 ...
1
vote
0answers
10 views

Can mAP score be used to describe “recall” rate of a model?

I have a general question regarding the mAP score used in measuring object detection system performance. I understood how the ...
2
votes
0answers
38 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 ...
1
vote
1answer
37 views

How do I identify the number and type of objects in the same picture?

I need to identify the number and type of all objects in a picture, so there can be multiple objects of the same type. For example, I have a picture with $10$ animals, and I want my program to tell ...
0
votes
0answers
17 views

How can I convert the annotations produced by LabelImg to labels for Yolov2?

I was recommended to use LabelImg to create annotation labels for YOLOv2. However, the annotations look something like this: 4 0.517500 0.597500 0.915000 0.735000 (classes and 4 coordinates x,y,w,h)...
0
votes
1answer
94 views

How to Mask an image using Numpy/OpenCV?

I am detecting wheels with a deep learning algorithm. The algorithm gives me the coordinates of those rectangles. I want to keep data that is in the rectangles of the image. I created rectangles as a ...
0
votes
0answers
10 views

When should I stop the object detection model training while mAP are not stable?

I am re-training the SSD MobileNet with 900 images from the Berkeley Deep Drive dataset, and eval towards 100 images from that dataset. The problem is that after ...
2
votes
1answer
51 views

How should I detect an object in a camera image?

I would like to create a model, that will tell me if one type of object is in an image or not. So, for example, I have a camera and I would like to see when one object gets into the shot. Object ...
2
votes
0answers
41 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 ...
0
votes
1answer
59 views

YOLO Architecture - kmeans clustering

In YOLO, why use k-means clustering to determine bounding-box priors ? Why if we use standard k-means with Euclidean distance, larger boxes generate more error than smaller boxes? Why using IOU (...
2
votes
0answers
21 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 ...
0
votes
0answers
15 views

Issues related to RoI Pooling in keras

I am trying to do RoI pooling of an image whose RoI bounding box coordinates are known to me. Can anyone provide me the code for doing the same? I have read many repositories but I didn't get any ...
2
votes
1answer
42 views

How do I locate a specific object in an image?

Some pictures contain an elephant, others don't. I know which of the pictures contain the elephant, but I don't know where it is or how does it look like. How do I make a neural network which ...
1
vote
0answers
11 views

Understanding average precision (AP) in measuring object detector performance

I am trying to understand the average precision (AP) metrics in evaluating the performance of deep-learning based object detection models. Suppose we have the following ground true (four objects ...
0
votes
1answer
17 views

From what aspect to measure the performance of an object detector?

I am on the hook to measure the prediction results of an object detector. I learned from some tutorials that when testing a trained object detector, for each object in the test image, the following ...
0
votes
0answers
61 views

YOLO architecture

1) How (Is it possible) to combine Fast-RCNN (2-stage) and YOLO (1-stage)? 2) Why with the addition of anchor boxes we changed the resolution to 416 x 416? Why using anchor boxes we get a small ...
0
votes
1answer
42 views

Any library recommended for recognizing squares in an image?

What do you recommend for recognizing squares in an image? The data needed to know is: Identify concrete squares. Identify the pixel coordinates of (the edges of) the squares in the image. A couple ...
2
votes
0answers
60 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 ...
0
votes
2answers
69 views

How do I perform object detection if there is only one type of object?

How do I do object detection (or identify the location of an object) if there is only one kind of object, and they are more of less similar size, but the picture does not look like standard scenes (it ...