Object detection is a computer vision approach for detecting things in photos and videos. To identify the needed object, object detection makes use of the specific and unique attributes of each type. The object detection model will look for central locations from where the creation of the particular round entity is conceivable while looking for a circular object. Face recognition and object tracking are two applications of such identification techniques. These are some algorithms that are used in objection detection.
Histogram of Oriented Gradients (HOG)
The histogram of oriented gradients is a feature descriptor used in computer vision and image processing for the purpose of object detection. The technique counts occurrences of gradient orientation in localized portions of an image. To better understand this algorithm you can use the below video link. https://www.youtube.com/watch?v=4ESLTAd3IOM
Python 57 Version:Current
Python 57 Version:Current License: No License
Region-based Convolutional Neural Networks (R-CNN)
The object detection approach using region-based convolutional neural networks is an enhancement over HOG's prior methods. Using selective features, we strive to extract the most important features (typically around 2000 features) in R-CNN models. A selective search method that can achieve these more important regional recommendations can be used to compute the process of picking the most significant extractions. To better understand of this algorithm you can use the below video link. https://www.youtube.com/watch?v=Z9nCBtaEb_g
Python 26 Version:v1.0
Python 26 Version:v1.0 License: Permissive (MIT)
Python 9 Version:Current
Python 9 Version:Current License: No License
Faster R-CNN
In the fast R-CNN method, the entire image is passed through the pre-trained Convolutional Neural Network instead of considering all the sub-segments. The region of interest (RoI) pooling is a special method that takes two inputs of the pre-trained model and selective search algorithm to provide a fully connected layer with an output. To better understand of this algorithm you can use the below video link. https://www.youtube.com/watch?v=Xycec1paxOo
Python 7816 Version:Current
Python 7816 Version:Current License: Others (Non-SPDX)
Single Shot Detector (SSD)
Single Shot Detector (SSD) is an object detection model. The SSD model detects the object in a single pass over the input image, unlike other models which traverse the image more than once to get an output detection. To better understand of this algorithm you can use the below video link. https://www.youtube.com/watch?v=NUEim5bF0_0
Python 75 Version:v0.1-alpha
Python 75 Version:v0.1-alpha License: Permissive (MIT)
Python 118 Version:Current
Python 118 Version:Current License: Strong Copyleft (GPL-3.0)
YOLO (You Only Look Once)
YOLO is an abbreviation for the term 'You Only Look Once'. This algorithm detects and recognizes various objects in a picture (in real-time). Object detection in YOLO is done as a regression problem and provides the class probabilities of the detected images.YOLO algorithm employs convolutional neural networks (CNN) to detect objects in real-time. To better understand this algorithm you can use the below video link. https://www.youtube.com/watch?v=MhftoBaoZpg
Python 2544 Version:v5.0
Python 2544 Version:v5.0 License: Strong Copyleft (GPL-3.0)
Python 200 Version:v0.1
Python 200 Version:v0.1 License: Weak Copyleft (LGPL-3.0)
RetinaNet
RetinaNet is one of the best one-stage object detection models that has proven to work well with dense and small-scale objects. RetinaNet has been formed by making two improvements over existing single-stage object detection models - Feature Pyramid Networks (FPN) and Focal Loss. To better understand this algorithm you can use the below video link. https://www.youtube.com/watch?v=mr8Y_Nuxciw
Python 4322 Version:1.0.0
Python 4322 Version:1.0.0 License: Permissive (Apache-2.0)
Python 1950 Version:Current
Python 1950 Version:Current License: Permissive (Apache-2.0)
Open Weaver – Develop Applications Faster with Open Source