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).
Questions tagged [object-detection]
230 questions
2
votes
0 answers
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 author say they give the same perfect mAP, while…
Hesham Eraqi
- 121
- 3
1
vote
0 answers
CBIR and object detection
How does CBIR (content based image recognition) fit into the problem of object detection? Let's say we want to detect 4 types of dogs (Golden Retriever, Cocker Spaniel, Greyhound, and Labrador). We have an "average" model trained using YOLOv3. So…
neeraj
- 31
- 3
1
vote
0 answers
Similarity of Images (CBIR) for two different cameras
Suppose we have a top down picture of an object (let's say it is a shoe) from an overhead camera. Also suppose we have a database of various objects from a closeup camera. If we feed the top-down picture of the hsoe into a CBIR model, then this…
ekjrhebrhje
- 11
- 1
1
vote
1 answer
Object Detection Algorithm that detects four corners of arbitrary quadrilateral, not just perpendicular rectangular
Is there some established Object Detection algorithm that is able to detect the four corners of an arbitrary quadrilateral (x0,y0,x1,y1,x2,y2,x3,y3) as opposed to the more typical perpendicular rectangular (x,y,w,h) ?
Loop
- 135
- 6
1
vote
1 answer
Two Models vs One Model for Person Detection and Object Detection
Is it possible to do person detection and object detection within one model? The training data would be images annotated with bounding boxes for objects and people. Because normally object detection and person detection are done separately? Is…
NebulousReveal
- 113
- 5
1
vote
0 answers
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 AP score is calculated, by averaging precision over recall 0 to 1. And then we can compute mAP, by averaging AP score of…
lllllllllllll
- 239
- 1
- 6
0
votes
2 answers
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 would like the model to learn that: "if the…
Raymond Pang
- 103
- 2
-1
votes
1 answer
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 the person but a bitmap marking which pixels are…
jaboja
- 101
- 3