Meta tags:
description=A large-scale object counting framework that is cost- and time-efficient.;
keywords=satellite imagery, remote sensing, generative networks, generative modeling, pixel synthesis, super resolution;

Headings (most frequently used words):

the, to, in, count, of, distribution, building, is, object, counting, from, proposal, subfig, ground, truth, see, results, for, different, methods, map, and, large, scale, satellite, images, with, covariate, based, importance, sampling, visualization, distributions, africa, learned, population, density, raster, represents, quite, well, most, ideal, case, we, want, be, proportional, abstract, paper, citation, method, an, illustration, framework, comparison, exhaustive, approach, estimating, counts, click, on, options, above, drag, zoom, us, states, african, countries, error, rate, estimation, using, averaged, over, 20, runs, related, work,

Text of the page (most frequently used words):
the (62), count (17), object (16), and (16), #distribution (12), sampling (11), from (10), satellite (10), #proposal (8), that (7), large (7), importance (7), building (7), images (7), are (6), website (6), high (6), exhaustive (6), counting (6), population (6), with (6), ground (6), counts (6), imagery (5), for (5), region (5), over (5), cost (5), compared (5), truth (5), covariate (5), estimation (5), using (5), approach (5), this (4), resolution (4), estimating (4), all (4), target (4), isotonic (4), identity (4), data (4), error (4), small (4), number (4), you (3), code (3), image (3), human (3), method (3), results (3), show (3), purchasing (3), while (3), map (3), different (3), states (3), can (3), estimate (3), total (3), africa (3), subfig (3), scale (3), based (3), which (2), want (2), prior (2), works (2), use (2), also (2), mapping (2), tiles (2), approaches (2), huge (2), amount (2), hours (2), statistics (2), contrast (2), ayush (2), 2021 (2), converges (2), sample (2), uniform (2), performance (2), fewer (2), still (2), achieving (2), methods (2), see (2), african (2), countries (2), few (2), specifically (2), estimated (2), given (2), buildings (2), representative (2), base (2), areas (2), raster (2), however (2), expensive (2), framework (2), chenlin (2), meng (2), enci (2), liu (2), willie (2), neiswanger (2), jiaming (2), song (2), marshall (2), burke (2), david (2), lobell (2), stefano (2), ermon (2), aaai (2), paper (2), detection (2), survey (2), collection (2), geographies (2), means, free, borrow, just, ask, link, back, page, footer, please, remember, remove, analytics, included, header, not, your, source, licensed, under, creative, commons, attribution, sharealike, international, license, format, borrowed, project, nerfies, there, poverty, level, recent, have, achieved, great, success, collecting, labelling, exhaustively, nevertheless, these, require, long, annotation, often, unaffortable, researchers, inflexible, update, interested, developing, more, time, efficient, loop, pipeline, utilizing, 2021b, 2018, crowther, 2015, 2020, related, work, found, fastest, groundtruth, tuned, faster, size, increases, experiment, baseline, incorporating, knowledge, via, boosts, requires, much, labeling, accuracies, rate, averaged, runs, click, options, above, drag, zoom, regions, 001, low, computed, below, absolute, difference, between, microsoft, footprints, google, open, divided, saves, constructing, real, major, steps, described, follows, finally, samples, labeled, annotators, next, learn, either, fine, tune, latter, regression, then, select, informative, first, construct, rasters, take, pixel, value, normalized, pixels, within, probability, downloads, covering, maps, objects, each, trained, model, takes, summation, produce, illustration, comparison, appear, proc, 36th, conference, artificial, intelligence, 2022, bibtex, coming, soon, citation, arxiv, 2112, 09126, emerging, scalable, alternative, many, environmental, socioeconomic, monitoring, applications, performing, prohibitively, due, compute, inspired, traditional, strategies, propose, through, budget, our, selects, learnable, able, accurately, after, processing, only, fraction, empirically, proposed, achieves, strong, united, cars, kenya, brick, kilns, bangladesh, swimming, pools, requiring, abstract, visualization, distributions, learned, density, represents, quite, well, most, ideal, case, proportional, colab, stanford, university,

Text of the page (random words):
is count large scale object counting from satellite images with covariate based importance sampling is count large scale object counting from satellite images with covariate based importance sampling chenlin meng enci liu willie neiswanger jiaming song marshall burke david b lobell stefano ermon stanford university paper code colab visualization of distributions in africa the proposal distribution learned from the population density raster subfig c represents the ground truth building distribution subfig d quite well in the most ideal case we want the proposal distribution to be proportional to the ground truth abstract object detection in high resolution satellite imagery is emerging as a scalable alternative to on the ground survey data collection in many environmental and socioeconomic monitoring applications however performing object detection over large geographies can still be prohibitively expensive due to the high cost of purchasing imagery and compute inspired by traditional survey data collection strategies we propose an approach to estimate object count statistics over large geographies through sampling given a cost budget our method selects a small number of representative areas by sampling from a learnable proposal distribution using importance sampling we are able to accurately estimate object counts after processing only a small fraction of the images compared to an exhaustive approach we show empirically that the proposed framework achieves strong performance on estimating the number of buildings in the united states and africa cars in kenya brick kilns in bangladesh and swimming pools in the u s while requiring as few as 0 01 of satellite images compared to an exhaustive approach paper arxiv 2112 09126 2021 citation chenlin meng enci liu willie neiswanger jiaming song marshall burke david b lobell stefano ermon is count large scale object counting from satellite images with covariate based importance sampling to appear in proc 36th aaai conference on artificial intelligence aaai 2022 bibtex coming soon method an illustration of the is count framework in comparison to the exhaustive approach to object counting an exhaustive approach subfig a downloads all image tiles covering the target region maps the objects in each image using a trained model and takes the summation of counts in all the images to produce a total count however purchasing satellite imagery for a large target region can be expensive in contrast is count saves a huge amount of cost by constructing a proposal distribution that is representative of the real object distribution the major steps in is count is described as follows first we construct the base distribution from the covariate rasters i e population nl specifically we take the pixel value normalized over all raster pixels within the target region as the probability to sample it next we learn the proposal distribution using either identity mapping from the base distribution or fine tune the latter with isotonic regression then we select a small number of informative areas for object counting by sampling from the proposal distribution finally the small number of samples are labeled by human annotators and the total object count is estimated using importance sampling estimating building counts we can use is count to estimate the total object count in different regions with as few as 0 001 of the data while achieving estimation error as low as 1 0 specifically the estimation error is computed as the absolute difference between the estimated and the ground truth counts given by the microsoft building footprints in the us and google open buildings in africa divided by the ground truth we show the estimation error map of building counts in the us states and african countries below uniform nl identity nl isotonic population identity population isotonic click on the options above to see results for different methods drag the map and zoom in to see results for the us states and african countries error rate map of building count estimation using different methods averaged over 20 runs compared to exhaustive approaches is count requires much fewer cost e g 0 01 on purchasing high resolution satellite images and fewer hours on labeling while still achieving high accuracies on estimating object counts building count experiment results show that incorporating prior knowledge from covariate data via importance sampling boosts the estimation performance compared to the uniform sampling baseline we also found that is count with tuned proposal distribution converges faster to the ground truth object count as the sample size increases that is the population isotonic proposal distribution converges fastest to the groundtruth building count compared to the population identity method related work there are prior works that use high resolution satellite imagery for estimating poverty level ayush et al 2020 ayush et al 2021 also recent works have achieved great success in object mapping by collecting and labelling all satellite image tiles in a target region exhaustively crowther et al 2015 yu et al 2018 yi et al 2021b nevertheless these exhaustive approaches require huge amount of high resolution satellite imagery over a large region and long hours of human annotation which are often unaffortable to researchers and inflexible to update statistics in contrast we are interested in developing a more cost and time efficient human in the loop object counting pipeline by utilizing importance sampling the format of the website is borrowed from the nerfies project website this website is licensed under a creative commons attribution sharealike 4 0 international license this means you are free to borrow the source code of this website we just ask that you link back to this page in the footer please remember to remove the analytics code included in the header of the website which you do not want on your website