Bird-Count: a multi-modality benchmark and system for bird population counting in the wild
Authors: 
Hongchang Wang, Huaxiang Lu, Huimin Guo, Haifang Jian, Chuang Gan, Wu LiuAuthors Info & Claims
Hongchang Wang, Huaxiang Lu, Huimin Guo, Haifang Jian, Chuang Gan, Wu LiuAuthors Info & ClaimsPages 45293 - 45315
Abstract
The fluctuation of the bird population reflects the change in the ecosystem, which plays a vital role in ecosystem conservation. However, manual counting is still the mainstream method for bird population counting, which is time-consuming and laborious. One major bottleneck in developing efficient, accurate, and intelligent learning algorithms to counting birds is the lack of large-scale datasets. In this paper, the first large-scale bird population counting dataset, named Bird-Count, with multi-modality morphology annotations is proposed. This paper first evaluates various state-of-the-art (SOTA) models for crowd counting on the Bird-Count and gets poor results. The reason is that the forms, appearances, and postures among different birds are more variant than the crowd. To mitigate these challenges, a simple yet effective plug-and-play framework, called Morphology Prior Knowledge Fusion Network (MPKNet), which can be used on-site to help generate a high-precision bird population density map by incorporating morphological prior knowledge, is proposed. Comprehensive evaluations show that the proposed method can reduce the error rate by 6.02% compared with the current SOTA crowd counting algorithms on average. Moreover, with the above technologies, the intelligent bird population monitoring system is deployed in several important wetland national nature reserves for bird protection.
References
[1]
Agrawal D, Minocha S, Namasudra S, Kumar S (2021) Ensemble algorithm using transfer learning for sheep breed classification. In: 2021 IEEE 15th International symposium on applied computational intelligence and informatics (SACI). IEEE, pp 199–204
[2]
Arteta C, Lempitsky V, Zisserman A (2016) Counting in the wild. In: European conference on computer vision. Springer, pp 483–498
[3]
Buckland ST Point-transect surveys for songbirds: robust methodologies Auk 2006 123 2 345-357
[4]
Cao X, Wang Z, Zhao Y, Su F (2018) Scale aggregation network for accurate and efficient crowd counting. In: ECCV, pp 734–750
[5]
Chakraborty R, Verma G, and Namasudra S Ifodpso-based multi-level image segmentation scheme aided with masi entropy J Ambient Intell Humanized Comput 2021 12 7 7793-7811
[6]
Chen K, Loy CC, Gong S, Xiang T (2012) Feature mining for localised crowd counting. In: BMVC, pp 1–11
[7]
Chen L, Wang G, and Hou G Multi-scale and multi-column convolutional neural network for crowd density estimation Multimed Tools Appl 2021 80 5 6661-6674
[8]
Devi D, Namasudra S, and Kadry S A boosting-aided adaptive cluster-based undersampling approach for treatment of class imbalance problem Int J Data Warehous Min (IJDWM) 2020 16 3 60-86
[9]
Fu H, Ma H, Xiao H (2014) Crowd counting via head detection and motion flow estimation. In: ACM multimedia, pp 877–880
[10]
Grenzdörffer G Uas-based automatic bird count of a common gull colony Int Arch Photogramm Remote Sens Spat Inf Sci 2013 1 2
[11]
Hooshmand MK and Gad I Feature selection approach using ensemble learning for network anomaly detection CAAI Trans Intell Technol 2020 5 4 283-293
[12]
Huang S, Li X, Cheng ZQ, Zhang Z, Hauptmann A (2020) Stacked pooling for boosting scale invariance of crowd counting. In: IEEE ICASSP, pp 2578–2582
[13]
Idrees H, Saleemi I, Seibert C, Shah M (2013) Multi-source multi-scale counting in extremely dense crowd images. In: IEEE CVPR, pp 2547–2554
[14]
Jiang X, Xiao Z, Zhang B, Zhen X, Cao X, Doermann D, Shao L (2019) Crowd counting and density estimation by trellis encoder-decoder networks. In: IEEE CVPR, pp 6133–6142
[15]
Kasper-Eulaers M, Hahn N, Berger S, Sebulonsen T, Myrland Ø, and Kummervold PE Detecting heavy goods vehicles in rest areas in winter conditions using yolov5 Algorithms 2021 14 4 114
[16]
Keller JM, Gray MR, Givens JA (1985) A fuzzy k-nearest neighbor algorithm. IEEE Trans Syst Man Cybern (4):580–585
[17]
Li Y, Zhang X, Chen D (2018) Csrnet: dilated convolutional neural networks for understanding the highly congested scenes. In: IEEE CVPR, pp 1091–1100
[18]
Liu W, Anguelov D, Erhan D, Szegedy C, Reed SE, Fu C, Berg AC (2016) Ssd: single shot multibox detector. In: ECCV, pp 21–37
[19]
Liu W, Salzmann M, Fua P (2019) Context-aware crowd counting. In: IEEE CVPR, pp 5099–5108
[20]
Ma Z, Wei X, Hong X, Gong Y (2020) Bayesian loss for crowd count estimation with point supervision. In: IEEE CVPR, pp 6142–6151
[21]
Namasudra S (2020) Fast and secure data accessing by using dna computing for the cloud environment. IEEE Trans Serv Comput
[22]
Namasudra S, Chakraborty R, Majumder A, and Moparthi NR Securing multimedia by using dna-based encryption in the cloud computing environment ACM Trans Multimed Comput Commun Appl (TOMM) 2020 16 3s 1-19
[23]
Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, et al. Pytorch: an imperative style, high-performance deep learning library NeurIPS 2019 32 8026-8037
[24]
Ren S, He K, Girshick RB, and Sun J Faster r-cnn: towards real-time object detection with region proposal networks NeurIPS 2017 28 91-99
[25]
Sam DB, Surya S, Babu RV (2017) Switching convolutional neural network for crowd counting. In: IEEE CVPR, pp 5744–5752
[26]
Sebastián-González E, Camp RJ, Tanimoto AM, de Oliveira PM, Lima BB, Marques TA, Hart PJ (2018) Density estimation of sound-producing terrestrial animals using single automatic acoustic recorders and distance sampling. Avian Conservation and Ecology
[27]
Shen Z, Xu Y, Ni B, Wang M, Hu J, Yang X (2018) Crowd counting via adversarial cross-scale consistency pursuit. In: IEEE CVPR, pp 5245–5254
[28]
Sindagi VA, Patel VM (2017) Generating high-quality crowd density maps using contextual pyramid cnns. In: IEEE ICCV, pp 1861–1870
[29]
Szegedy C, Ioffe S, Vanhoucke V, Alemi A (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI, pp 4278–4284
[30]
Tan X, Tao C, Ren T, Tang J, Wu G (2019) Crowd counting via multi-layer regression. In: ACM multimedia, pp 1907–1915
[31]
Viola P, Jones MJ, and Snow D Detecting pedestrians using patterns of motion and appearance Int J Comput Vis 2005 63 2 153-161
[32]
Wang M, Wang X (2011) Automatic adaptation of a generic pedestrian detector to a specific traffic scene. In: IEEE CVPR, pp 3401–3408
[33]
Wang C, Zhang H, Yang L, Liu S, Cao X (2015) Deep people counting in extremely dense crowds. In: ACM multimedia, pp 1299–1302
[34]
Wang Q, Gao J, Lin W, and Li X Nwpu-crowd: a large-scale benchmark for crowd counting and localization IEEE Trans Pattern Anal Mach Intell 2020 43 6 2141-2149
[35]
Wu B, Nevatia R (2005) Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. In: IEEE ICCV, pp 90–97
[36]
Yan Z, Yuan Y, Zuo W, Tan X, Wang Y, Wen S, Ding E (2019) Perspective-guided convolution networks for crowd counting. In: IEEE CVPR, pp 952–961
[37]
Zeng L, Xu X, Cai B, Qiu S, Zhang T (2017) Multi-scale convolutional neural networks for crowd counting. In: IEEE ICIP, pp 465–469
[38]
Zhang C, Li H, Wang X, Yang X (2015) Cross-scene crowd counting via deep convolutional neural networks. In: IEEE CVPR, pp 833–841
[39]
Zhang Y, Zhou D, Chen S, Gao S, Ma Y (2016) Single-image crowd counting via multi-column convolutional neural network. In: IEEE CVPR, pp 589–597
[40]
Zhou X, Wang D, Krähenbühl P (2019) Objects as points. arXiv:1904.07850, pp 1–12
[41]
Zou Z, Li C, Zheng Y, and Xu S Two stages double attention convolutional neural network for crowd counting Multimed Tools Appl 2020 79 39 29145-29159
Index Terms
- Bird-Count: a multi-modality benchmark and system for bird population counting in the wild
Index terms have been assigned to the content through auto-classification.
Recommendations
Correlation Clustering of Bird Sounds
Pattern RecognitionAbstractBird sound classification is the task of relating any sound recording to those species of bird that can be heard in the recording. Here, we study bird sound clustering, the task of deciding for any pair of sound recordings whether the same species ...
Optical flow-based bird tracking and counting for congregating flocks
ACIIDS'12: Proceedings of the 4th Asian conference on Intelligent Information and Database Systems - Volume Part IIIBird flock counting is not deeply studied yet, but there are applications of bird flock counting that would provide benefits to different parties, such as the population estimation of swiftlets for swiftlet farmers and migratory raptors for ...
CDPNet: conformer-based dual path joint modeling network for bird sound recognition
AbstractBird species monitoring is important for the preservation of biological diversity because it provides fundamental information for biodiversity assessment and protection. Automatic acoustic recognition is considered to be an essential technology ...
Comments
Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Publisher
Kluwer Academic Publishers
United States
Publication History
Published: 29 April 2023
Accepted: 06 February 2023
Revision received: 30 June 2022
Received: 20 October 2021
Author Tags
Qualifiers
- Research-article
Funding Sources
- the Chinese Academy of Sciences
- National Outstanding Youth Science Fund Project of National Natural Science Foundation of China
- the Leading Project of the Chinese Academy of Sciences (CAS)
- The High Technology Project
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 14 Jan 2025