17853313621's starred repositories
SfMLearner
An unsupervised learning framework for depth and ego-motion estimation from monocular videos
FlowNetPytorch
Pytorch implementation of FlowNet by Dosovitskiy et al.
SC-SfMLearner-Release
Unsupervised Scale-consistent Depth Learning from Video (IJCV2021 & NeurIPS 2019)
ssd-pytorch
这是一个ssd-pytorch的源码，可以用于训练自己的模型。
dogs_vs_cats
猫狗大战
MonoDepth-PyTorch
Unofficial implementation of Unsupervised Monocular Depth Estimation neural network MonoDepth in PyTorch
flownet2-tf
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Revisiting_Single_Depth_Estimation
official implementation of "Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries"
Emotion-Detection-in-Videos
The aim of this work is to recognize the six emotions (happiness, sadness, disgust, surprise, fear and anger) based on human facial expressions extracted from videos. To achieve this, we are considering people of different ethnicity, age and gender where each one of them reacts very different when they express their emotions. We collected a data set of 149 videos that included short videos from both, females and males, expressing each of the the emotions described before. The data set was built by students and each of them recorded a video expressing all the emotions with no directions or instructions at all. Some videos included more body parts than others. In other cases, videos have objects in the background an even different light setups. We wanted this to be as general as possible with no restrictions at all, so it could be a very good indicator of our main goal. The code detect_faces.py just detects faces from the video and we saved this video in the dimension 240x320. Using this algorithm creates shaky videos. Thus we then stabilized all videos. This can be done via a code or online free stabilizers are also available. After which we used the stabilized videos and ran it through code emotion_classification_videos_faces.py. in the code we developed a method to extract features based on histogram of dense optical flows (HOF) and we used a support vector machine (SVM) classifier to tackle the recognition problem. For each video at each frame we extracted optical flows. Optical flows measure the motion relative to an observer between two frames at each point of them. Therefore, at each point in the image you will have two values that describes the vector representing the motion between the two frames: the magnitude and the angle. In our case, since videos have a resolution of 240x320, each frame will have a feature descriptor of dimensions 240x320x2. So, the final video descriptor will have a dimension of #framesx240x320x2. In order to make a video comparable to other inputs (because inputs of different length will not be comparable with each other), we need to somehow find a way to summarize the video into a single descriptor. We achieve this by calculating a histogram of the optical flows. This is, separate the extracted flows into categories and count the number of flows for each category. In more details, we split the scene into a grid of s by s bins (10 in this case) in order to record the location of each feature, and then categorized the direction of the flow as one of the 8 different motion directions considered in this problem. After this, we count for each direction the number of flows occurring in each direction bin. Finally, we end up with an s by s by 8 bins descriptor per each frame. Now, the summarizing step for each video could be the average of the histograms in each grid (average pooling method) or we could just pick the maximum value of the histograms by grid throughout all the frames on a video (max pooling For the classification process, we used support vector machine (SVM) with a non linear kernel classifier, discussed in class, to recognize the new facial expressions. We also considered a Naïve Bayes classifier, but it is widely known that svm outperforms the last method in the computer vision field. A confusion matrix can be made to plot results better.
LiteFlowNet2
A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization, TPAMI 2020
LKVOLearner
Learning Depth from Monocular Videos using Direct Methods, CVPR 2018
Depth-Map-Prediction
Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
dogsVScats
图像二分类问题 猫狗大战 pytorch CNN
X-ray-classification
X-ray Images (Chest images) analysis and anomaly detection using Transfer learning with inception v2
cats-vs-dogs
TensorFlow实现Kaggle猫狗大战
AnoGAN-WGAN-pytorch
WGAN based AnoGAN
anomaly-detection-image-completion
This repository implements the approach to detect surface anomalies in images presented in the paper Anomaly Detection using Deep Learning based Image Completion: https://arxiv.org/pdf/1811.06861.pdf
Video-Anomaly-Detection
一种视频图像异常的检测算法，用python实现
Activity-Recognition
This Project is Vision-Based Activity Recognition targets to learn how to detect a human body from a video and describe the activity of the Human using Computer Vision method such as HOG (Histogram of Gradients) and HOF (Histogram of Optical Flow) descriptors to Extract Features and use Machine-Learning Technique SVM(Support Vector Machine) and KNN(K-Nearest Neighbors) Classifier to Classify and Recognition the human activity
Anomaly-Detection-for-ECAL-DQM
Code for supervised and semi-supervised (conv. autoencoder) based anomal detection system study for images of CMS electromagnetic calorimeter Data Quality Monitoring system