Counting Objects by Blockwise Classification

Liu, Liang; Lü, Hao; Xiong, Haipeng; Xian, Ke; Cao, Zhiguo; Shen, Chunhua

doi:10.1109/tcsvt.2019.2942970

Cited by 46 publications

(56 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In local count modeling, there are two ways to define a counter in the closed set [0, C max ], i.e., counting by regression [10], [25] and counting by classification [49], [23].…”

Section: Closed-set Countermentioning

confidence: 99%

From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer

Xiong

Liu

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

153

107

View full text Add to dashboard Cite

Visual counting, a task that aims to estimate the number of objects from an image/video, is an open-set problem by nature, i.e., the number of population can vary in [0, +∞) in theory. However, collected data and labeled instances are limited in reality, which means that only a small closed set is observed. Existing methods typically model this task in a regression manner, while they are prone to suffer from an unseen scene with counts out of the scope of the closed set. In fact, counting has an interesting and exclusive property-spatially decomposable. A dense region can always be divided until sub-region counts are within the previously observed closed set. We therefore introduce the idea of spatial divide-and-conquer (S-DC) that transforms open-set counting into a closed-set problem. This idea is implemented by a novel Supervised Spatial Divide-and-Conquer Network (SS-DCNet). Thus, SS-DCNet can only learn from a closed set but generalize well to open-set scenarios via S-DC. SS-DCNet is also efficient. To avoid repeatedly computing sub-region convolutional features, S-DC is executed on the feature map instead of on the input image. We provide theoretical analyses as well as a controlled experiment on toy data, demonstrating why closed-set modeling makes sense. Extensive experiments show that SS-DCNet achieves the state-of-the-art performance on three crowd counting datasets (ShanghaiTech, UCF_CC_50 and UCF-QNRF), a vehicle counting dataset (TRANCOS) and a plant counting dataset (MTC), with a 7.7% relative improvement on the UCF-QNRF, 33.1% on the TRANCOS, and 26.4% on the MTC. SS-DCNet also reports the state-of-the-art cross-domain performance on crowd counting datasets. Particularly in the task from UCF-QNRF to ShanghaiTech Part_A, SS-DCNet even beats most existing models trained directly on the target domain. Code and models have been made available at: https://tinyurl.com/SS-DCNet.

show abstract

“…In local count modeling, there are two ways to define a counter in the closed set [0, C max ], i.e., counting by regression [10], [25] and counting by classification [49], [23].…”

Section: Closed-set Countermentioning

confidence: 99%

From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer

Xiong

Liu

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

153

107

View full text Add to dashboard Cite

show abstract

“…where N gt ðb j Þ is the ground truth count of patch b j . Given the count map, following [24], we further quantize the count map to obtain the class map Cðb j Þ by…”

Section: Learning Targetmentioning

confidence: 99%

“…where pðj, cÞ is the probability of the j-th block for the c-th counting interval, C Max is the maximum counting interval, and C gt ðjÞ is the ground truth counting interval of the j-th block. At the inferring stage, to recover the count map from the class map, the median of each interval is set as its count value [24], i.e.,…”

Section: Learning Targetmentioning

confidence: 99%

See 1 more Smart Citation

High-Throughput Rice Density Estimation from Transplantation to Tillering Stages Using Deep Networks

Liu

et al. 2020

Plant Phenomics

Self Cite

View full text Add to dashboard Cite

Rice density is closely related to yield estimation, growth diagnosis, cultivated area statistics, and management and damage evaluation. Currently, rice density estimation heavily relies on manual sampling and counting, which is inefficient and inaccurate. With the prevalence of digital imagery, computer vision (CV) technology emerges as a promising alternative to automate this task. However, challenges of an in-field environment, such as illumination, scale, and appearance variations, render gaps for deploying CV methods. To fill these gaps towards accurate rice density estimation, we propose a deep learning-based approach called the Scale-Fusion Counting Classification Network (SFC2Net) that integrates several state-of-the-art computer vision ideas. In particular, SFC2Net addresses appearance and illumination changes by employing a multicolumn pretrained network and multilayer feature fusion to enhance feature representation. To ameliorate sample imbalance engendered by scale, SFC2Net follows a recent blockwise classification idea. We validate SFC2Net on a new rice plant counting (RPC) dataset collected from two field sites in China from 2010 to 2013. Experimental results show that SFC2Net achieves highly accurate counting performance on the RPC dataset with a mean absolute error (MAE) of 25.51, a root mean square error (MSE) of 38.06, a relative MAE of 3.82%, and a R2 of 0.98, which exhibits a relative improvement of 48.2% w.r.t. MAE over the conventional counting approach CSRNet. Further, SFC2Net provides high-throughput processing capability, with 16.7 frames per second on 1024×1024 images. Our results suggest that manual rice counting can be safely replaced by SFC2Net at early growth stages. Code and models are available online at https://git.io/sfc2net.

show abstract

“…The density map is generated from dotted annotations with Gaussian smoothing such that each pixel is assigned with a value that corresponds to the object density, which transforms counting into a dense prediction problem (Lu et al, 2019 , 2020 ). It has become the basic building block for many object counting models (Chen et al, 2013 ; Arteta et al, 2014 ) including recent deep counting networks (Zhang et al, 2015 , 2016 ; Sindagi and Patel, 2017 ; Li et al, 2018 ; Liu et al, 2020 ; Ma et al, 2019 ; Xiong et al, 2019b ). Most state-of-the-art counting networks, however, are also inefficient due to the use of pretrained VGG-16, which hinders their applicability in high-resolution imagery in plant counting.…”

Section: Introductionmentioning

confidence: 99%

TasselNetV2+: A Fast Implementation for High-Throughput Plant Counting From High-Resolution RGB Imagery

Lü

2020

Front. Plant Sci.

Self Cite

View full text Add to dashboard Cite

Plant counting runs through almost every stage of agricultural production from seed breeding, germination, cultivation, fertilization, pollination to yield estimation, and harvesting. With the prevalence of digital cameras, graphics processing units and deep learning-based computer vision technology, plant counting has gradually shifted from traditional manual observation to vision-based automated solutions. One of popular solutions is a state-of-the-art object detection technique called Faster R-CNN where plant counts can be estimated from the number of bounding boxes detected. It has become a standard configuration for many plant counting systems in plant phenotyping. Faster R-CNN, however, is expensive in computation, particularly when dealing with high-resolution images. Unfortunately high-resolution imagery is frequently used in modern plant phenotyping platforms such as unmanned aerial vehicles, engendering inefficient image analysis. Such inefficiency largely limits the throughput of a phenotyping system. The goal of this work hence is to provide an effective and efficient tool for high-throughput plant counting from high-resolution RGB imagery. In contrast to conventional object detection, we encourage another promising paradigm termed object counting where plant counts are directly regressed from images, without detecting bounding boxes. In this work, by profiling the computational bottleneck, we implement a fast version of a state-of-the-art plant counting model TasselNetV2 with several minor yet effective modifications. We also provide insights why these modifications make sense. This fast version, TasselNetV2+, runs an order of magnitude faster than TasselNetV2, achieving around 30 fps on image resolution of 1980 × 1080, while it still retains the same level of counting accuracy. We validate its effectiveness on three plant counting tasks, including wheat ears counting, maize tassels counting, and sorghum heads counting. To encourage the use of this tool, our implementation has been made available online at https://tinyurl.com/TasselNetV2plus.

show abstract

Counting Objects by Blockwise Classification

Cited by 46 publications

References 38 publications

From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer

From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer

High-Throughput Rice Density Estimation from Transplantation to Tillering Stages Using Deep Networks

TasselNetV2+: A Fast Implementation for High-Throughput Plant Counting From High-Resolution RGB Imagery

Contact Info

Product

Resources

About