Limits...
Camera sensor arrangement for crop/weed detection accuracy in agronomic images.

Romeo J, Guerrero JM, Montalvo M, Emmi L, Guijarro M, Gonzalez-de-Santos P, Pajares G - Sensors (Basel) (2013)

Bottom Line: In Precision Agriculture, images coming from camera-based sensors are commonly used for weed identification and crop line detection, either to apply specific treatments or for vehicle guidance purposes.Accuracy of identification and detection is an important issue to be addressed in image processing.There are two main types of parameters affecting the accuracy of the images, namely: (a) extrinsic, related to the sensor's positioning in the tractor; (b) intrinsic, related to the sensor specifications, such as CCD resolution, focal length or iris aperture, among others.

View Article: PubMed Central - PubMed

Affiliation: Department of Software Engineering and Artificial Intelligence, Faculty of Informatics, Complutense University, Madrid 28040, Spain. jromeo99@hotmail.com

ABSTRACT
In Precision Agriculture, images coming from camera-based sensors are commonly used for weed identification and crop line detection, either to apply specific treatments or for vehicle guidance purposes. Accuracy of identification and detection is an important issue to be addressed in image processing. There are two main types of parameters affecting the accuracy of the images, namely: (a) extrinsic, related to the sensor's positioning in the tractor; (b) intrinsic, related to the sensor specifications, such as CCD resolution, focal length or iris aperture, among others. Moreover, in agricultural applications, the uncontrolled illumination, existing in outdoor environments, is also an important factor affecting the image accuracy. This paper is exclusively focused on two main issues, always with the goal to achieve the highest image accuracy in Precision Agriculture applications, making the following two main contributions: (a) camera sensor arrangement, to adjust extrinsic parameters and (b) design of strategies for controlling the adverse illumination effects.

Show MeSH

Related in: MedlinePlus

(a) Original saturated image; (b) binary image after segmentation.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3673087&req=5

f12-sensors-13-04348: (a) Original saturated image; (b) binary image after segmentation.

Mentions: The exposure time for the image in Figure 4(a) was below which it would be desirable, unlike the one obtained in the image in Figure 4(b), which was sufficient. As we can see, the result in the first case is worse than in the second one. Indeed, the binary image displayed in Figure 11(b) contains an over-segmentation in the part of interest, where crop lines and weeds are placed with important gaps on the outer part. A possible explanation to this phenomenon is that the sensor requires sufficient time to be impacted by the reflectance and the illumination coming from objects in the scene. Because there are different types of materials, the reflectance and illumination sent to the sensors is different for each type of material. When the exposure time is insufficient, the sensor produces this kind of effect. On the contrary, if the exposure time is excessive the intensity image becomes saturated and the image segmentation process fails. Figure 12(a) displays a saturated image and its corresponding segmented image in Figure 12(b) using the same segmentation procedure as before; we can see how the result becomes unfeasible. From the point of view of weeds and crop lines detection, this leads to clear inaccuracies.


Camera sensor arrangement for crop/weed detection accuracy in agronomic images.

Romeo J, Guerrero JM, Montalvo M, Emmi L, Guijarro M, Gonzalez-de-Santos P, Pajares G - Sensors (Basel) (2013)

(a) Original saturated image; (b) binary image after segmentation.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3673087&req=5

f12-sensors-13-04348: (a) Original saturated image; (b) binary image after segmentation.
Mentions: The exposure time for the image in Figure 4(a) was below which it would be desirable, unlike the one obtained in the image in Figure 4(b), which was sufficient. As we can see, the result in the first case is worse than in the second one. Indeed, the binary image displayed in Figure 11(b) contains an over-segmentation in the part of interest, where crop lines and weeds are placed with important gaps on the outer part. A possible explanation to this phenomenon is that the sensor requires sufficient time to be impacted by the reflectance and the illumination coming from objects in the scene. Because there are different types of materials, the reflectance and illumination sent to the sensors is different for each type of material. When the exposure time is insufficient, the sensor produces this kind of effect. On the contrary, if the exposure time is excessive the intensity image becomes saturated and the image segmentation process fails. Figure 12(a) displays a saturated image and its corresponding segmented image in Figure 12(b) using the same segmentation procedure as before; we can see how the result becomes unfeasible. From the point of view of weeds and crop lines detection, this leads to clear inaccuracies.

Bottom Line: In Precision Agriculture, images coming from camera-based sensors are commonly used for weed identification and crop line detection, either to apply specific treatments or for vehicle guidance purposes.Accuracy of identification and detection is an important issue to be addressed in image processing.There are two main types of parameters affecting the accuracy of the images, namely: (a) extrinsic, related to the sensor's positioning in the tractor; (b) intrinsic, related to the sensor specifications, such as CCD resolution, focal length or iris aperture, among others.

View Article: PubMed Central - PubMed

Affiliation: Department of Software Engineering and Artificial Intelligence, Faculty of Informatics, Complutense University, Madrid 28040, Spain. jromeo99@hotmail.com

ABSTRACT
In Precision Agriculture, images coming from camera-based sensors are commonly used for weed identification and crop line detection, either to apply specific treatments or for vehicle guidance purposes. Accuracy of identification and detection is an important issue to be addressed in image processing. There are two main types of parameters affecting the accuracy of the images, namely: (a) extrinsic, related to the sensor's positioning in the tractor; (b) intrinsic, related to the sensor specifications, such as CCD resolution, focal length or iris aperture, among others. Moreover, in agricultural applications, the uncontrolled illumination, existing in outdoor environments, is also an important factor affecting the image accuracy. This paper is exclusively focused on two main issues, always with the goal to achieve the highest image accuracy in Precision Agriculture applications, making the following two main contributions: (a) camera sensor arrangement, to adjust extrinsic parameters and (b) design of strategies for controlling the adverse illumination effects.

Show MeSH
Related in: MedlinePlus