The Experts below are selected from a list of 116739 Experts worldwide ranked by ideXlab platform
Alessandro L Koerich - One of the best experts on this subject based on the ideXlab platform.
-
ICASSP - Visual and acoustic identification of Bird Species
2015 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2015Co-Authors: Andreia Marini, A. J. Turatti, Alceu S. Britto, Alessandro L KoerichAbstract:This paper presents a novel approach for Bird Species identification that relies on both visual features extracted from unconstrained Bird images and acoustic features extracted from Bird vocalizations. The Scale Invariant Feature Transform (SIFT) detects local features in Bird images, which are then used to train a support vector machine classifier. The instances that are not classified with a certain degree of certainty are then rejected and reclassified using Mel-frequency cepstral coefficients (MFCCs) extracted from the Bird songs if available. Experiments conducted on a dataset of 50 Bird Species that comprise images from the CUB200-2011 and audio samples from Xeno-Canto have shown that improvements between 1.2 and 15.7 percentage points are achieved when using an acoustic classifier to re-process the instances rejected by the visual classifier, depending on the rejection level.
-
SMC - Bird Species Classification Based on Color Features
2013 IEEE International Conference on Systems Man and Cybernetics, 2013Co-Authors: Andreia Marini, Jacques Facon, Alessandro L KoerichAbstract:This paper presents a novel approach for Bird Species classification based on color features extracted from unconstrained images. This means that the Birds may appear in different scenarios as well may present different poses, sizes and angles of view. Besides, the images present strong variations in illuminations and parts of the Birds may be occluded by other elements of the scenario. The proposed approach first applies a color segmentation algorithm in an attempt to eliminate background elements and to delimit candidate regions where the Bird may be present within the image. Next, the image is split into component planes and from each plane, normalized color histograms are computed from these candidate regions. After aggregation processing is employed to reduce the number of the intervals of the histograms to a fixed number of bins. The histogram bins are used as feature vectors to by a learning algorithm to try to distinguish between the different numbers of Bird Species. Experimental results on the CUB-200 dataset show that the segmentation algorithm achieves 75% of correct segmentation rate. Furthermore, the Bird Species classification rate varies between 90% and 8%, depending on the number of classes taken into account.
-
automatic Bird Species identification for large number of Species
International Symposium on Multimedia, 2011Co-Authors: Marcelo Teider Lopes, Lucas L Gioppo, Thiago T Higushi, Celso A A Kaestner, Carlos N Silla, Alessandro L KoerichAbstract:In this paper we focus on the automatic identification of Bird Species from their audio recorded song. Bird monitoring is important to perform several tasks, such as to evaluate the quality of their living environment or to monitor dangerous situations to planes caused by Birds near airports. We deal with the Bird Species identification problem using signal processing and machine learning techniques. First, features are extracted from the Bird recorded songs using specific audio treatment, next the problem is performed according to a classical machine learning scenario, where a labeled database of previously known Bird songs are employed to create a decision procedure that is used to predict the Species of a new Bird song. Experiments are conducted in a dataset of recorded songs of Bird Species which appear in a specific region. The experimental results compare the performance obtained in different situations, encompassing the complete audio signals, as recorded in the field, and short audio segments (pulses) obtained from the signals by a split procedure. The influence of the number of classes (Bird Species) in the identification accuracy is also evaluated.
-
SMC - Feature set comparison for automatic Bird Species identification
2011 IEEE International Conference on Systems Man and Cybernetics, 2011Co-Authors: Marcelo Teider Lopes, Alessandro L Koerich, Carlos Nascimento Silla Junior, Celso A A KaestnerAbstract:This paper deals with the automated Bird Species identification problem, in which it is necessary to identify the Species of a Bird from its audio recorded song. This is a clever way to monitor biodiversity in ecosystems, since it is an indirect non-invasive way of evaluation. Different features sets which summarize in different aspects the audio properties of the audio signal are evaluated in this paper together with machine learning algorithms, such as probabilistic, instance-based, decision trees, neural networks and support vector machines. Experiments are conducted in a dataset of recorded songs of three Bird Species. The experimental results compare the performance of the features sets and different classifiers showing that it is possible to obtain very promising results in the automated Bird Species identification problem.
-
ISM - Automatic Bird Species Identification for Large Number of Species
2011 IEEE International Symposium on Multimedia, 2011Co-Authors: Marcelo Teider Lopes, Lucas L Gioppo, Thiago T Higushi, Celso A A Kaestner, Carlos N Silla, Alessandro L KoerichAbstract:In this paper we focus on the automatic identification of Bird Species from their audio recorded song. Bird monitoring is important to perform several tasks, such as to evaluate the quality of their living environment or to monitor dangerous situations to planes caused by Birds near airports. We deal with the Bird Species identification problem using signal processing and machine learning techniques. First, features are extracted from the Bird recorded songs using specific audio treatment, next the problem is performed according to a classical machine learning scenario, where a labeled database of previously known Bird songs are employed to create a decision procedure that is used to predict the Species of a new Bird song. Experiments are conducted in a dataset of recorded songs of Bird Species which appear in a specific region. The experimental results compare the performance obtained in different situations, encompassing the complete audio signals, as recorded in the field, and short audio segments (pulses) obtained from the signals by a split procedure. The influence of the number of classes (Bird Species) in the identification accuracy is also evaluated.
Aki Harma - One of the best experts on this subject based on the ideXlab platform.
-
automatic identification of Bird Species based on sinusoidal modeling of syllables
International Conference on Acoustics Speech and Signal Processing, 2003Co-Authors: Aki HarmaAbstract:Syllables are elementary building blocks of Bird song. In the sounds of many songBirds, a large class of syllables can be approximated as amplitude and frequency varying brief sinusoidal pulses. We test how well Bird Species can be recognized by comparing simple sinusoidal representations of isolated syllables. Results are encouraging and show that, with limited sets of Bird Species, a recognizer based on this signal model may already be sufficient.
-
ICASSP (5) - Automatic identification of Bird Species based on sinusoidal modeling of syllables
2003 IEEE International Conference on Acoustics Speech and Signal Processing 2003. Proceedings. (ICASSP '03)., 1Co-Authors: Aki HarmaAbstract:Syllables are elementary building blocks of Bird song. In the sounds of many songBirds, a large class of syllables can be approximated as amplitude and frequency varying brief sinusoidal pulses. We test how well Bird Species can be recognized by comparing simple sinusoidal representations of isolated syllables. Results are encouraging and show that, with limited sets of Bird Species, a recognizer based on this signal model may already be sufficient.
Andreia Marini - One of the best experts on this subject based on the ideXlab platform.
-
ICASSP - Visual and acoustic identification of Bird Species
2015 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2015Co-Authors: Andreia Marini, A. J. Turatti, Alceu S. Britto, Alessandro L KoerichAbstract:This paper presents a novel approach for Bird Species identification that relies on both visual features extracted from unconstrained Bird images and acoustic features extracted from Bird vocalizations. The Scale Invariant Feature Transform (SIFT) detects local features in Bird images, which are then used to train a support vector machine classifier. The instances that are not classified with a certain degree of certainty are then rejected and reclassified using Mel-frequency cepstral coefficients (MFCCs) extracted from the Bird songs if available. Experiments conducted on a dataset of 50 Bird Species that comprise images from the CUB200-2011 and audio samples from Xeno-Canto have shown that improvements between 1.2 and 15.7 percentage points are achieved when using an acoustic classifier to re-process the instances rejected by the visual classifier, depending on the rejection level.
-
SMC - Bird Species Classification Based on Color Features
2013 IEEE International Conference on Systems Man and Cybernetics, 2013Co-Authors: Andreia Marini, Jacques Facon, Alessandro L KoerichAbstract:This paper presents a novel approach for Bird Species classification based on color features extracted from unconstrained images. This means that the Birds may appear in different scenarios as well may present different poses, sizes and angles of view. Besides, the images present strong variations in illuminations and parts of the Birds may be occluded by other elements of the scenario. The proposed approach first applies a color segmentation algorithm in an attempt to eliminate background elements and to delimit candidate regions where the Bird may be present within the image. Next, the image is split into component planes and from each plane, normalized color histograms are computed from these candidate regions. After aggregation processing is employed to reduce the number of the intervals of the histograms to a fixed number of bins. The histogram bins are used as feature vectors to by a learning algorithm to try to distinguish between the different numbers of Bird Species. Experimental results on the CUB-200 dataset show that the segmentation algorithm achieves 75% of correct segmentation rate. Furthermore, the Bird Species classification rate varies between 90% and 8%, depending on the number of classes taken into account.
Gang Feng - One of the best experts on this subject based on the ideXlab platform.
-
Threatened Bird Species are concentrated in regions with less historical human impacts
Biological Conservation, 2021Co-Authors: Xueting Yang, Alice C. Hughes, Gang FengAbstract:Abstract Previous human activities have a lasting influence on modern biodiversity patterns, especially on the distribution of threatened Species. China is a large country, with a high population and a long history of agriculture, but is also a megadiverse country, with over 1370 Bird Species and over 300 threatened Bird Species. As far as we know, this study is the first attempt to test the associations between distribution of proportion of threatened Bird Species and anthropogenic activities (changes in forest cover, cropland area and population density) over different periods (between 1700 and 1800, between 1800 and 1900, and between 1900 and 2000). We show that there are higher proportions of threatened Bird Species in Northern China, especially Northeastern and Northwestern China. Notably, both ordinary least squares models and simultaneous autoregressive models indicate that higher proportions of threatened Bird Species were largely associated with less historical anthropogenic activities, i.e., smaller changes in forest cover and cropland area in Northern China between 1700 and 1800. These findings emphasize the role of historical land use changes in shaping current distribution of threatened Bird Species, and highlight the importance of avoiding further anthropogenic activities in the last-of-the-wild regions for biodiversity conservation.
Frank Dziock - One of the best experts on this subject based on the ideXlab platform.
-
What determines occurrence of threatened Bird Species on urban wastelands
Biological Conservation, 2012Co-Authors: Peter J. Meffert, Frank DziockAbstract:Abstract Bird Species of cultivated landscapes have been declining dramatically for decades. The main cause for this decline is intensified agricultural practice. At the same time, worldwide urbanisation increases and has severe impacts on land use. Urban wastelands, i.e., unused land within urban agglomerations, are known to provide habitat for endangered animals, but to date systematic research on Birds is rare. We aim at assessing environmental characteristics of urban wastelands that meet the requirements of rare and declining Bird Species. In the city of Berlin, Germany, we surveyed Birds on 55 wasteland sites dominated by sparse vegetation. Our analysis includes quantitative measurements of residential human density and degree of sealing at different spatial scales, a detailed vegetation mapping, and data on human intrusion. Boosted regression trees were used to model the occurrence of eight Bird Species of European Conservation concern (SPEC). Overall we found 12 SPEC Species; for eight data were sufficient to built models. Our findings reveal that the occurrence of endangered Bird Species depends most strongly on area size and vegetation structure and to a lesser extent on the composition of the urban matrix. On-site features accounted for roughly two third of the explained variance and degree of urbanisation in the surroundings for the remaining one third. Intrusion of humans or dogs had no measurable negative effect on Species occurrence. As a rule of thumb, plots above 5 ha harbour SPEC Species, those above 7 ha are valuable for several sensitive open-land Bird Species. We show that wasteland habitats have potential for nature conservation that should be considered by urban planners and landscape architects. Knowledge about crucial habitat features (few trees and shrubs, sparse vegetation) enables us to create and maintain urban green spaces that enhance protection of rare and declining Species. Urban wastelands may not have the potential to fully compensate for changes and population declines outside urban areas, but they may help to offset the loss of biodiversity in the countryside.