Prerequisite knowledge of attitude detection

Challenges of attitude detection:

1. The number of people in each picture is unknown;
2. The interaction between people is complicated (contact, occlusion, etc.), making it difficult to detect some key points;
3. The more people in the image, the greater the time cost, making real time application difficult;

Detection Indicator

• PCK , Percentage of Correct Keypoints, the proportion of key points that are correctly estimated. Calculate the ratio of the normalized distance between the detection key point and the corresponding ground-truth less than the set threshold. The FLIC data set uses the torso size as a normalized reference; the MPII data set uses the head length as a normalized reference.
• PDJ , Percentage of Detected Joints, the ratio of detected key points.
• OKS , Object Keypoint Similarity, calculates the similarity between ground-truth and key points of the human body, inspired by IoU.
• OKS matrix.
• AP , Average Precision, among all OKS, count the proportion of joint points that are larger than the threshold t.
• mAP , mean Average Precision, given a different threshold t, the mean value of AP.
  $$OK{S}_p=\frac{{\sum }_i\exp (\frac{-d_{p_i}^2}{2S_p^2{\sigma }_i^2})\delta (v_{p_i}=1)}{{\sum }_i\delta (v_{p_i}=1)}$$
  Where $p$ represents the id of the person in the ground-truth,$i$ represents the id of keypoint,$d_{p_i}$Represents the Euclidean distance between ground-truth and prediction key point, $S_p$Represents the scale factor of the current person, ${\sigma }_i$Represents the normalization factor of the i-th key point (this factor is obtained from the standard deviation of all ground-truth calculations of the dataset, reflecting the standard deviation of the current bone annotation, $The$ larger the$\sigma ,\; the$ more difficult it is to label),$v_{p_i}$Indicates whether the i-th joint point of the p-th person is visible, $The\; delta$ function is a function used to select the visible points for calculation, and is a Boolean function.

Method classification

• The top-down method first detects the person (target detection), and after the detection frame is obtained, the single person (target) key point detection (single person pose estimation) is performed.
• Bottom-up method , first detect all the nodes of everyone, and then group and parallel the joints to combine adults

  Generally, the top-down method has higher accuracy (a two-stage structure of target detection first, and then joint point detection), and the bottom-up method is faster.

• In 2016, CPM, Hourglass, was the SOTA algorithm used for detection and estimation at the time;
• In 2016, the method used by OpenPose was the champion of COCO key point detection;
• In 2017, CPN was the champion of COCO key point detection;
• In 2018, MSPN was the champion of COCO key point detection;
• In 2019, MSPA's xxx proposed HRNet, which verified the importance of spatial resolution;