Benjamin Weinstein's Projects
Implementation of the LiDAR tree segmentation algorithm, Layer Stacking.
R package for airborne LiDAR data manipulation and visualisation for forestry application
Task Overview Following the success of the four previous plant identification tasks (ImageCLEF 2011-13 ; LifeCLEF 2014), we are glad to organize this year a new challenge dedicated to botanical data. The task will be focused on tree, herbs and ferns species identification based on different types of images. Its main novelties compared to the last years will by : -"use of external resources" : it will be possible to use more external online resources (but strictly forbidden to used data from Tela Botanica website), as training data to enrich the provided one, - "species number" : the number of species (about 1 000 species), which is an important step towards covering the entire flora of a given region. Multi-image query The motivation of the task is to fit better with a real scenario where one user tries to identify a plant by observing its different organs, such as it has been demonstrated in [MAED2012]. Indeed, botanists usually observe simultaneously several organs like the leaves and the fruits or the flowers in order to disambiguate species which could be confused if only one organ were observed. Moreover, if only one organ is observed, such as the bark of a deciduous plant during winter where nothing else is observable, then the observation of this organ with several photos related to different point of views could be more informative than only one point of view. Thus, contrary to the 3 first years, the species identification task won't be image-centered but OBSERVATION-centered. The aim of the task is be to produce a list of relevant species for each observation of a plant of the test dataset, i.e. one or a set of several pictures related to a same event: one same person photographing several detailed views on various organs the same day with the same device with the same lightening conditions observing one same plant.
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
xarray add-on
new repo for GeoHackweek2019
Repo for the visualization used to make the complex systems video
MCGC approach to individual tree crown delineation
Tree delineation from lidar using mean shift clustering
OCR for plotwatcher video date, time, and camera ID extraction.
Deployment Repo for computer vision, OCR, and parsing of plotwatcer images. The partner repo to MeerkatReader which is static for the manuscript.
Machine Learning for Wildlife Image Classification
Using Tensorflow MobileNets to train a hummingbird object detector
Active Repo for Dev.
Source Repo for MotionMeerkat for Bisque Directory
This repository is sister to OpenCV_HummingbirdsMotion and contains all the assorted material that goes with the MotionMeerkat publication in Methods in Ecology and Evolution
Wrangling NEON vegetation structure (vst) for integration with Airborne Observation Platform (AOP) remote sensing data
A two method analysis for qualitative networks.
Strong trait-matching despite shifting resources in a tropical plant-pollinator network
Brownian Motion Simulations for Ecological Networks
Hummingbird networks through time
test workshop
Natural Language Toolkit (NLTK) lesson materials
Course website
A Hierarchical Model for Species Interaction Networks
Semantic3D segmentation with Open3D and PointNet++
Motion Detection using OpenCV and python