Multi-modal Registration Using a Combined Similarity Measure

Wachs, Juan P.; Stern, Helman I.; Burks, T.F.; Alchanatis, V.

doi:10.1007/978-3-540-88079-0_16

Cited by 6 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, this article proposes to introduce CIoU to solve the shortcomings of IoU. CIoU is a very good distance metric, which can replace the loss function of border regression in most target detection algorithms, as shown in equations ( 1)- (3).…”

Section: Border Regression Loss Function Based On Cioumentioning

confidence: 99%

See 1 more Smart Citation

Immature Apple Detection Method Based on Improved Yolov3

Huang

Zhang

Liu

et al. 2021

ASP trans. Internet things

View full text Add to dashboard Cite

The identification of immature apples is a key technical link to realize automatic real-time monitoring of orchards, expert decision-making, and realization of orchard output prediction. In the orchard scene, the reflection caused by light and the color of immature apples are highly similar to the leaves, especially the obscuration and overlap of fruits by leaves and branches, which brings great challenges to the detection of immature apples. This paper proposes an improved YOLOv3 detection method for immature apples in the orchard scene. Use CSPDarknet53 as the backbone network of the model, introduce the CIOU target frame regression mechanism, and combine with the Mosaic algorithm to improve the detection accuracy. For the data set with severely occluded fruits, the F1 and mAP of the immature apple recognition model proposed in this article are 0.652 and 0.675, respectively. The inference speed for a single 416×416 picture is 12 ms, the detection speed can reach 83 frames/s on 1080ti, and the inference speed is 8.6 ms. Therefore, for the severely occluded immature apple data set, the method proposed in this article has a significant detection effect, and provides a feasible solution for the automation and mechanization of the apple industry.

show abstract

Section: Border Regression Loss Function Based On Cioumentioning

confidence: 99%

“…Automated harvesting requires accurate detection and recognition of the fruit within a tree canopy in real-time in uncontrolled environments. However, occlusion, variable illumination, variable appearance and texture make this task a complex challenge [3].…”

Section: Introductionmentioning

confidence: 99%

Immature Apple Detection Method Based on Improved Yolov3

Huang

Zhang

Liu

et al. 2021

ASP trans. Internet things

View full text Add to dashboard Cite

show abstract

“…Furthermore, the combination of different similarity techniques has been widely proposed (Arevalillo‐Herraez et al, 2008; Wachs et al, 2009) where usually the registration parameters are weighted according to the strength of each measure.…”

Section: Proposed Techniquementioning

confidence: 99%

Optical Analysis of Strength Tests Based on Block‐Matching Techniques

Rodríguez

Rabuñal

Pérez

et al. 2011

Computer aided Civil Eng

View full text Add to dashboard Cite

One of the main issues in civil engineering is to analyze the behavior of materials in strength tests. Traditionally, information about displacements and strains in the materials is carried out from these tests using physical devices such as strain gauges or other transducers.Although these devices provide accurate and robust measurements in a wide range of situations, they are limited to obtaining measurements in a single point of the material and in a single direction of the movement, thus, the global behavior of the material cannot be analyzed.The proposed technique consists of the integration of a calibration process with a block-matching algorithm to measure displacements from images. This algorithm uses the similarity between regions in the images to extract the 2D vector displacement field from each point, and to quantify the strain on the surface of the material.The proposed algorithm has been designed to measure displacements from real images of material surfaces taken during strength tests, and it has the advantages of being robust with long-range displacements, of perform- * To whom correspondence should be addressed. E-mail: arodriguezta @udc.es.ing the analysis on the image space domain (avoiding the problems related to the use of Fourier Transforms), and of measurements in long sequences related to a real point of the material and not to a pixel position. C 2011 Computer-Aided Civil and Infrastructure Engineering.

show abstract

“…Uma das aplicações da termografia óptica é a estimação do número de frutas em pomares (BULANON et al, 2008;WACHS et al, 2009). A detecção é baseada na suposição de que a temperatura do fruto é diferente dos arredores da cena.…”

Section: -Imagens Por Termografia óPticaunclassified

“…Os níveis de infecção estão classificados de acordo com a escala de notação visual (1: 0-1%, 2: 1-5%, 3: 5-10%, 4: 10-25%, 5: 25-50%, 6: 50-75%, 7: 75-100%). As colunas de 1-7 representam estas classificações: (A) imagem visível de irregularidade na folha codificada; (B) estado inicial da imagem fluorescente; (C) eficiência quântica da imagem fluorescente; (D) imagens térmicas em Kelvin (BELIN et al, 2013).Uma das aplicações da termografia óptica é a estimação do número de frutas em pomares (BULANON et al, 2008;WACHS et al, 2009). A detecção é baseada na suposição de que a temperatura do fruto é diferente dos arredores da cena.…”

unclassified

Fusão sensorial por classificação cognitiva ponderada no mapeamento de cenas naturais agrícolas para análise quali-quantitativa em citricultura

Lulio¹

View full text Add to dashboard Cite

Computer systems are used in Precision Agriculture (PA) to provide relational sampling, accuracy and data processing required for agricultural practices and schemes, which are not common to conventional agriculture, demanding higher costs of production and research directed to the remote sensing for mapping and inspection of crop rows. Tasks are carried out using a priori On-the-Go sensors, and proprioceptive and exteroceptive ones, embedded instrumentation, geographic information and existing implements on production and farming, which these activities ensure during the steps of planting, maturation, maintenance and harvesting of a particular culture. Also, these tasks are aided with the use of terrestrial agricultural mobile robots such as autonomous vehicle platforms for locomotion between the crop rows in the acquisition of field data. Given this information and relating the investment and development of these technologies, the goal of this work is to assist the inspection, quantification and qualification of agricultural crops (citrus) of planting area through analyzing and identifying data for sensor fusion, associated with digital image processing, optical thermal imaging and optical flow sensors and reflectance, based on the extraction of real natural scenes objects, identifying items such as fruits, grasses, stems, branches and leaves, thus providing a qualitative and quantitative set of data analyzed culture. As of a computer vision system and sensor fusion, Gigabit Ethernet cameras, sonars, thermal camera, infrared optical flow sensors and monochrome CMOS sensors are embedded in two sides of the vehicle structure, with the same geometric center ratio of the agricultural mobile robot. After data acquisition, image and signal processing techniques are applied for non homogeneous region segmentation, and pattern recognition through statistical classifiers. Such techniques are programmed in MATLAB and OpenCV, embedded in a computer platform. Cognitive classifiers that perform pattern and classes matching are intended on a combination of weighted data fusion techniques, that during locomotion of the agricultural mobile robot, the steps of image processing and combination of parameters for classification are manipulated for analysis retrospectively, conflicting existing data with likely changes resulting in culture and biomass. Figura 3.6: Na sequência de imagens acima, da esquerda para direita tem-se a imagem visível, imagem NIR e imagem UVFL; na sequência de imagens abaixo, da esquerda para direita temse a imagem do fruto com irregularidade, segmentação usando CART, e segmentação usando LDA (Adaptado de BLASCO et al., 2007b) Figura 3.7: Etapas de segmentação e classificação, considerando o índice de diferença normalizado, o filtro de variância, componentes Cb e Cr, e inserção de rótulo no objeto encontrado, separado do plano de fundo (PAYNE et al., 2013) Figura 3.8: Imagens multimodais registradas de folhas de macieiras, apresentando sete níveis de patógenos que causam irregularidades na superfície, 21 d...

show abstract

Multi-modal Registration Using a Combined Similarity Measure

Cited by 6 publications

References 8 publications

Immature Apple Detection Method Based on Improved Yolov3

Immature Apple Detection Method Based on Improved Yolov3

Optical Analysis of Strength Tests Based on Block‐Matching Techniques

Fusão sensorial por classificação cognitiva ponderada no mapeamento de cenas naturais agrícolas para análise quali-quantitativa em citricultura

Contact Info

Product

Resources

About