Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 2 de 2
Filter
Add more filters










Database
Language
Publication year range
1.
Sensors (Basel) ; 24(6)2024 Mar 19.
Article in English | MEDLINE | ID: mdl-38544224

ABSTRACT

Scene recognition is the task of identifying the environment shown in an image. Spectral filter array cameras allow for fast capture of multispectral images. Scene recognition in multispectral images is usually performed after demosaicing the raw image. Along with adding latency, this makes the classification algorithm limited by the artifacts produced by the demosaicing process. This work explores scene recognition performed on raw spectral filter array images using convolutional neural networks. For this purpose, a new raw image dataset is collected for scene recognition with a spectral filter array camera. The classification is performed using a model constructed based on the pretrained Places-CNN. This model utilizes all nine channels of spectral information in the images. A label mapping scheme is also applied to classify the new dataset. Experiments are conducted with different pre-processing steps applied on the raw images and the results are compared. Higher-resolution images are found to perform better even if they contain mosaic patterns.

2.
J Insect Sci ; 13: 150, 2013.
Article in English | MEDLINE | ID: mdl-24766585

ABSTRACT

The sunn pest, Eurygaster integriceps Puton (Hemiptera: Scutelleridae), is the most important insect pest of wheat and barley. The population management of this pest is of major concern to wheat producers. One of the potential control strategies is to use entomopathogenic fungi. This study evaluates the pathogenicity of the fungus Metarhizium anisopliae var. major (Metchnikoff) Sorokin (Hypocreales: Clavicipitaceae) on the sunn pest, E. integriceps. Five concentrations of the fungus were utilized, ranging from 1×10(4) to 1×10(8) conidia/mL, accompanied by controls. Fifth instar nymphs and adults (a migratory summer population and a diapausing population) previously exposed to fungi were sown to isolate the fungi, and the growth parameters were analyzed. A direct spray technique was used to expose the isolates to the E. integriceps. The experiment was repeated four times, and mortalities of the insects for all treatments were recorded daily. The results showed that the mortality of infected nymphs was significantly higher than the mortality of control nymphs. Also, the longevity of infected adults was lower than the controls. The results also showed that diapausing adults of the sunn pest were much more susceptible to infection than the summer adults. Estimated LC50 values for the M14 isolate were 1.4 × 10(6), 1.4 ×10 (5) , and 2.3 × 10(3) spores/mL against the aestivation population, the diapausing population, and 5(th) instar nymphs, respectively. Estimated LT50 values using 10(8) spores/mL of the Mm isolate on the aestivation and diapausing populations were 11.9 and 5.11 days, respectively. The results demonstrated that M. anisoplaie was effective on all of stages of E. integriceps. In addition, the nymphal stage was more susceptible than the adults.


Subject(s)
Heteroptera/microbiology , Metarhizium , Pest Control, Biological , Animals , Diapause, Insect , Heteroptera/growth & development , Iran , Lethal Dose 50 , Nymph/growth & development
SELECTION OF CITATIONS
SEARCH DETAIL
...