Hi, the basic idea of Ostu is follows

Initially it works directly on the gray level histogram

Find the threshold that minimizes the weighted within-class variance

for detailed information check the following link

https://www.google.co.in/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&uact=8&ved=0ahUKEwia-f6OnpjMAhUFv5QKHV2TDUMQFgggMAA&url=https%3A%2F%2Fwebdocs.cs.ualberta.ca%2F~nray1%2FCMPUT605%2Ftrack3_papers%2Fotsu.ppt&usg=AFQjCNHoBt2EXNB3sx2uvqkRFrJe-fwzaA&bvm=bv.119745492,d.dGo

Hi, the basic idea of Ostu is follows

Initially it works directly on the gray level histogram

Find the threshold that minimizes the weighted within-class variance

for detailed information check the following link

https://www.google.co.in/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&uact=8&ved=0ahUKEwia-f6OnpjMAhUFv5QKHV2TDUMQFgggMAA&url=https%3A%2F%2Fwebdocs.cs.ualberta.ca%2F~nray1%2FCMPUT605%2Ftrack3_papers%2Fotsu.ppt&usg=AFQjCNHoBt2EXNB3sx2uvqkRFrJe-fwzaA&bvm=bv.119745492,d.dGo

Simply, it is an image thresholding algorithm for reduction of a gray level image to a binary image.

Segmentation is often considered to be the first step in image analysis.In general, autonomous segmentation is one of the most difficult tasks in digital image processing. Otsu’s thresholding chooses the threshold to minimize the intraclass variance of the thresholded black and white pixels.

U can take a look at the links below which are some tutorials providing the basics of OTSU thresholding:

http://www.math.tau.ac.il/~turkel/notes/otsu.pdf

http://web-ext.u-aizu.ac.jp/course/bmclass/documents/otsu1979.pdf

https://en.wikipedia.org/wiki/Otsu%27s_method

This is a good question. 

In addition to very good answers already given, there is a bit more to consider.   Articles on Otsu's method are available here on RG.   A good introduction to Otsu's method is given in

https://www.researchgate.net/publication/221196493_Image_Segmentation_Based_on_2D_Otsu_Method_with_Histogram_Analysis

See also:

https://www.researchgate.net/publication/238734218_An_improved_image_segmentation_algorithm_based_on_Otsu_method

https://www.researchgate.net/publication/224592999_Otsu_Method_and_K-means

https://www.researchgate.net/publication/259849226_11_IJFTET_-_Vol_4-Issue_1_Improved_Otsu's_Thresholding_Techniques_for_HSI_Color_Image_Segmentation

https://www.researchgate.net/publication/224085716_A_Fast_2D_Otsu_Thresholding_Algorithm_Based_on_Improved_Histogram

Conference Paper Image Segmentation Based on 2D Otsu Method with Histogram Analysis

Article An improved image segmentation algorithm based on Otsu method

Conference Paper Otsu Method and K-means

Article 11. IJFTET - Vol. 4-Issue 1_Improved Otsu's Thresholding Tec...

Conference Paper A Fast 2D Otsu Thresholding Algorithm Based on Improved Histogram

Response by Ranjit  is straight-forward but abstract. Otsu's algorithm is more sophisticated way of image thesholding as compared to traditional mean-based split of gray-level image into binary image. This sophistication comes from minimizing the weighted within-class variance and maximizing between-class variance, as quoted by Chethan and Singha.

A simple and fitting example can be found at:

http://www.labbookpages.co.uk/software/imgProc/otsuThreshold.html

Than you much my colleague Abdul Kayom Md Khairuzzaman  for your interesting answer.

Even though, Otsu method is quite fast. It has one drawback, it is required uniform illumination which is difficult in practice. You can use it in addition to any other method.

Can someone help me please, I would apply the otsu's method to calculate the adaptive threshold which can be used in threshold based fall detection

methods to improve the accuracy of fall detection. Is it possible ??

this useful

https://pdfs.semanticscholar.org/ee8b/aed71d46b4d8747c8f2c73ba73f7c4a06130.pdf

http://www.labbookpages.co.uk/software/imgProc/otsuThreshold.html

http://engr.case.edu/merat_francis/eecs490f07/lectures/lecture22.pdf