Visual AI

Industry Leading AI with Diverse Usages

Analyzing Physical Actions

Behavior analysis is a field in which people are detected from a visual input, with their actions then analyzed or their paths tracked based on pose estimation. Along with Face Analysis, this field is opening up new horizons for deep learning based intelligent video analytics.

The Top-Tier in Global
Person Recognition Technology

High rate of person re-identification

ALCHERA’s behavior analysis AI is capable of reidentifying people within ALCHERA’s own dataset with a high degree of accuracy.

High accuracy for the recognition of abnormal behavior

ALCHERA’s behavior analysis AI can recognize abnormal behaviors with the highest level of accuracy as we continue to conduct research for innovative technologies in the field of behavior recognition.

Achieving the Performance of
Human Eyes

Person Detection

Detects the location and dimensions of a person from a video input. The algorithm receives an image and estimates the top-left and bottom-right corners of the human area through convolution operation.

Person Pose Estimation

Estimates the position of human joint points. In an image of a person, the position of the joints is calculated as a probability value in the NxM Matrix of the same ratio as the image. The algorithm then estimates a more accurate position through post-processing.

Person Tracker

Tracks the same person in a series of images. For people detected in a continuous image frame, features are extracted using Appearance Feature and Motion Feature are used by the matching algorithm determine whether the two are of the same person.

Person Re-Identification

Recognizes a person from video input by learning his/her distinguishing features. An N-dimensional vector is extracted by performing a convolution operation on the human region detected in the image. The vector that is extracted is then used to represent an individual feature of a person, meaning that a specific person can be recognized based on those features.

Abnormal Behavior Recognition

Recognizes abnormal behaviors related to safety issues. The algorithm receives an RGB image or a sequence of joint position coordinates and performs a convolution operation to extract spatial and temporal feature vectors for the action. The actions are categorized based on an N-dimensional feature vector that includes all the features of a person's posture at each time step (Spatial) and how the posture changes over time (Temporal).

Various Real-life Applications

Video analytics for hotels, casinos, and hospitals

Video analytics for hotels, casinos, and hospitals

Person detection, person tracker and re-identification are used to track VIPs or patients so that they can be provided with a higher level of service.

Video analytics for hotels, casinos, and hospitals

Person detection, person tracker and re-identification are used to track VIPs or patients so that they can be provided with a higher level of service.

Video analytics for prevention of crime

Video analytics for prevention of crime

Action recognition enables detection of loitering, intrusion, running, and movement in wrong directions for prevention of crimes.

Video analytics for prevention of crime

Action recognition enables detection of loitering, intrusion, running, and movement in wrong directions for prevention of crimes.

Applications of Behavior Analysis

Access Control

A safe and convenient access management solution

...

...