jodyngo,jodyngo,github

real_time_object_detection

This repository contains the code for real-time object detection. I'm using video stream coming from webcam. MobileNet-SSD and OpenCv has been used as base-line approach. TensorFlow object detection API has been used in revised approach.

recursivebf

A lightweight C++ library for recursive bilateral filtering [Yang, Qingxiong. "Recursive bilateral filtering". European Conference on Computer Vision, 2012].

refinenet

RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation

remotevideoanalyzer

Linux client and server programs for streaming encoded video from a webcam via UDP for remote decoding/processing of the video.

resized-psnr

Resized-PSNR is an objective quality metric for omnidirectional video.

rst-saliency

Here is the code and saliency maps for the paper 'Saliency Pattern Detection by Ranking Structured Trees' in ICCV 2017.

s-measure

Structure-measure: A New Way to Evaluate Foreground Maps, ICCV 2017 (Spotlight)

sal_eval_toolbox

evaluation toolbox for salient object detection

saliency

Code for http://saliency.mit.edu/

saliency-2016-cvpr

Shallow and Deep Convolutional Networks for Saliency Prediction

saliency-detection-fdc

Fast Visual Saliency Based on Multi-scale Difference of Gaussians Fusion in Frequency Domain

saliency-evaluation-toolbox

This Toolbox contains E-measure, S-measure, weighted F & F-measure, MAE and PR curves or bar metrics for salient object detection.

saliency-salgan-2017

SalGAN: Visual Saliency Prediction with Generative Adversarial Networks

saliencydetection

Various Saliency Detection Implementation

saliencyevaluation

use precision, recall and F-measure to evaluate your saliency detection method

saliencyuncertainty_icme2016

Code for the paper - T. Alshawi, Z. Long, and G. AlRegib, “Understanding spatial correlation in eye-fixation maps for visual attention in videos,” Proceedings of IEEE International Conference on Multimedia and Expo (ICME), Seattle, WA, Nov. 2016.

saliencyuncertainty_tip2018

Code for the paper - T. Alshawi, Z. Long, and G. AlRegib, “Unsupervised uncertainty estimation using spatiotemporal cues in video saliency detection,” IEEE Transactions on Image Processing, vol. 27, no. 6, pp. 2818-2827, Jun. 2018.

scalable-video-codec-for-diverse-networking-conditions

Video streaming is gaining more and more popularity due to video based applications, and due to heterogeneous networking environment,a codec is needed that can facilitate every user according to his requirement which should be user friendly also. So by using H.264 video compression standard, we have developed a scalable video codec for such networking conditions. Purpose of choosing H.264 for compression is its ability to compress the video at a rate twice than previous standards while maintaining the quality of video. The main idea is to achieve compression, maintaining the quality and integrity of video. Scalability is achieved in such a way that video is encoded just once decoded but it can be decoded multiple times according to the requirement of user. All the three modes of scalable codec are covered and implemented; temporal, spatial and quality scalability with better results. In temporal scalability, scalability is achieved by varying the frame rate, in spatial; by varying the resolution and in quality by varying the bit rate of the input video. All the three modes split the video into different layers and then scalable codec is applied over them. Scalable codec is tested over different videos and better results are obtained in terms of scalability and compression.

jodyngo Goto Github PK

jodyngo's Projects

Recommend Projects

Recommend Topics

Recommend Org