See the various programming languages used and their attributes
I need someone to help me with a stereo visual SLAM/ stereo visual Odometry project. The subtasks in the project include among others: 1. Detection and description of ORB features. 2. Stereo matching/stereo calibration and rectification. 3. Generating a disparity map/depth map/point cloud. 4. Relative pose estimation and calculating the rotation matrix and translation vector using PnP method. 5. If the rotation matrix and translation vector are good enough, we can also start building a map and draw pose graph and optimize it. 6. The whole project should be implemented on ROS platform. Your profile (MUST HAVE): 1. Must have a good understanding of the concept of visual SLAM. 2. You must have very good C++ programming skills, opencv, computer vision and ROS platform. I have already done...
It is about detection (bounding boxes) and semantic segmentation. Need to be done in C++ with CMakelists binding, Linux environment. For detection, I used the HoG feature approach and trained the SVM classifier for the purpose of finding objects and the bounding boxes around them. Some tuning is needed because the results I get on the test image are currently meaningless. Scripts for training and creating a new dataset for SVM training purposes have been created. Also, the script related to the formation of a CNN-network for segmentation with the help of transfer-learning was developed in Python. Accuracy on the validation set was high, therefore it is only necessary to import the already trained TensorFlow model in C++ and create a test script.
This task is not code extensive. The task is to warp the given images to another with the given guidelines. The code for warping will be given, the task is to manually write the points for each target image and their corresponding point in the source image (in a separate code file for each image). Some knowledge regarding clothing (how a perfect saree shall look after warping) such as sarees, kurtis etc would be helpful. Some knowledge regarding warping images using Thin Plate Spline Shape Transformer (TPS) in python would be helpful as well. Note - Only 6 images to be done at the moment.
Main Task - Image Reconstruction 1. Custom image Dataset must be loaded from the local drive. As of now you can load your own dataset. 2. Image Augmentation have to be included Important: There should not be any restriction on the dimensions of the image. It will work with all the image dimensions Step 1: 3. The various types of Autoencoder techniques and GAN must compared with and without hyper parameter tuning, Ensembling methods with various performance metrics. 4. There is an option to mention and control the types of noises with the range 5. The reconstructed results will be checked with the bunch of images or else the single image with similarity score with the input image.
Hi, We are looking for a competent freelancer with good Expertise with Google cloud vision. To Help us resolve a road block Uploading Products on google via google vision api and improve Product search on google using images. Looking for a long-term working relationship. Regards