n1-k0

Code-mix

Cpp-C-Prime

C++ prime 5th

cs231n-Spring2019-assignment

This is the all answer for stanford course CS231n spring 2019.

deep_sort_pytorch

MOT tracking using deepsort and yolov3 with pytorch

geerpc

go-micro-demo

Posture-and-Fall-Detection-System-Using-3D-Motion-Sensors

This work presents a supervised learning approach for training a posture detection classifier, and implementing a fall detection system using the posture classification results as inputs with a Microsoft Kinect v2 sensor. The Kinect v2 skeleton tracking provides 3D depth coordinates for 25 body parts. We use these depth coordinates to extract seven features consisting of the height of the subject and six angles between certain body parts. These features are then fed into a fully connected neural network that outputs one of three considered postures for the subject: standing, sitting, or lying down. An average classification rate of over 99.30% for all three postures was achieved on test data consisting of multiple subjects where the subjects were not even facing the Kinect depth camera most of the time and were located in different locations. These results show the feasibility to classify human postures with the proposed setup independently of the location of the subject in the room and orientation to the 3D sensor.

Python_OpenNI2

Sample applications that use the official python wrappers for OpenNI 2 (opencv)

SOTS

Single object tracking and segmentation.

TracKit

[ECCV'20] Ocean: Object-aware Anchor-Free Tracking

n1-k0/Code-mix

n1-k0/Cpp-C-Prime

C++ prime 5th

n1-k0/cs231n-Spring2019-assignment

This is the all answer for stanford course CS231n spring 2019.

n1-k0/deep_sort_pytorch

MOT tracking using deepsort and yolov3 with pytorch

n1-k0/geerpc

n1-k0/go-micro-demo

n1-k0/Posture-and-Fall-Detection-System-Using-3D-Motion-Sensors

This work presents a supervised learning approach for training a posture detection classifier, and implementing a fall detection system using the posture classification results as inputs with a Microsoft Kinect v2 sensor. The Kinect v2 skeleton tracking provides 3D depth coordinates for 25 body parts. We use these depth coordinates to extract seven features consisting of the height of the subject and six angles between certain body parts. These features are then fed into a fully connected neural network that outputs one of three considered postures for the subject: standing, sitting, or lying down. An average classification rate of over 99.30% for all three postures was achieved on test data consisting of multiple subjects where the subjects were not even facing the Kinect depth camera most of the time and were located in different locations. These results show the feasibility to classify human postures with the proposed setup independently of the location of the subject in the room and orientation to the 3D sensor.

n1-k0/Python_OpenNI2

Sample applications that use the official python wrappers for OpenNI 2 (opencv)

n1-k0/SOTS

Single object tracking and segmentation.

n1-k0/pytracking

Visual tracking library based on PyTorch.

n1-k0/ruan-jian-kai-fa

n1-k0/siamban

Siamese Box Adaptive Network for Visual Tracking

n1-k0/sort

Simple, online, and realtime tracking of multiple objects in a video sequence.

n1-k0/tech

2021面试题，Java面试题、JVM面试题、多线程面试题、并发编程、设计模式面试题、Spring面试题、MyBatis面试题、ZooKeepe面试题r、Dubbo面试题、Elasticsearch面试题、Memcached面试题、MongoDB面试题、Redis面试题、MySQL面试题、RabbitMQ面试题、Kafka面试题、Linux面试题、Netty面试题、Tomcat面试题、Python面试题、HTML面试题、CSS面试题、Vue面试题、React面试题、JavaScript面试题、Android面试题

n1-k0/test

n1-k0/updatenet

Learning the Model Update for Siamese Trackers (ICCV 2019)

n1-k0/yolov5

YOLOv5 in PyTorch > ONNX > CoreML > TFLite