A weeding system for a railway weeding vehicle including at least one camera for mounting on a railway vehicle to acquire an image of a portion of a railway track while the railway vehicle is moving. The system also includes a spraying unit to be mounted on the railway vehicle, a control unit to receive images from the camera, generate a weed species detection signal and selectively cause the spraying of a chemical agent on the basis of the weed species detection signal. The control unit executes a training-based algorithm based on a set of reference images labeled to indicate the presence or not of at least one weed species in the images.

A weeding system for a railway weeding vehicle comprising a camera and a spraying unit with several supply modules, a nozzle and a controller module to receive a weed species detection signal and to command the spraying of chemical agent. The weeding system also comprises a weed species identification unit with a communication module, a memory module and a processing module having several parallel processing cores. Each parallel processing core performs a convolution operation between a sub-matrix constructed from nearby pixels of the image and a predefined kernel stored in the memory module to obtain a feature representation sub-matrix of the pixel values of the image. The processing module computes a probability of presence of a weed species from the feature representation matrix and generates a weed species detection signal.

A weeding system for a railway weeding vehicle comprising a camera and a spraying unit with several supply modules, a nozzle and a controller module to receive a weed species detection signal and to command the spraying of chemical agent. The weeding system also comprises a weed species identification unit with a communication module, a memory module and a processing module having several parallel processing cores. Each parallel processing core performs a convolution operation between a sub-matrix constructed from nearby pixels of the image and a predefined kernel stored in the memory module to obtain a feature representation sub-matrix of the pixel values of the image. The processing module computes a probability of presence of a weed species from the feature representation matrix and generates a weed species detection signal.

The present invention relates to a railway weed control vehicle. It is described to activate (110) at least one weed control unit to control weeds along and around a railway track. The railway track comprises rails and sleepers. The at least one electrode based weed control unit is mounted at at least one first position of the vehicle. Sensor data is acquired (120) by at least one sensor. The sensor data relates to at least one location along and around the railway track. The at least one sensor is mounted at at least one second position of the vehicle. With respect to a forward movement direction of the vehicle the at least one second position is in front of the at least one first position. The sensor data is provided (130) to a processing unit. The sensor data is analysed (140) by the processing unit to determine locations of rail infrastructure components in addition to the rails and sleepers. The processing unit modifies (150) activation of one or more electrode based weed control units of the at least one electrode based weed control unit comprising utilisation of at least one location of the determined locations of the rail infrastructure components.

The present invention relates to a railway weed control vehicle. It is described to activate (110) at least one weed control unit to control weeds along and around a railway track. The railway track comprises rails and sleepers. The at least one electrode based weed control unit is mounted at at least one first position of the vehicle. Sensor data is acquired (120) by at least one sensor. The sensor data relates to at least one location along and around the railway track. The at least one sensor is mounted at at least one second position of the vehicle. With respect to a forward movement direction of the vehicle the at least one second position is in front of the at least one first position. The sensor data is provided (130) to a processing unit. The sensor data is analysed (140) by the processing unit to determine locations of rail infrastructure components in addition to the rails and sleepers. The processing unit modifies (150) activation of one or more electrode based weed control units of the at least one electrode based weed control unit comprising utilisation of at least one location of the determined locations of the rail infrastructure components.

A weed control vehicle may include a sensor for acquiring data relating to at least one location of an environment using at least one sensor of the vehicle. The sensor data is provided to a processing unit of the vehicle. The processing unit determines a distance sensing result for each location of the at least one location. The processing unit controls at least one actuator to move at least one boom of the vehicle. At least one weed control unit is attached to the at least one boom. The processing unit controls the at least one actuator to move the at least one boom on the basis of the distance sensing result for each location of the at least one location.

A weed control vehicle may include a sensor for acquiring data relating to at least one location of an environment using at least one sensor of the vehicle. The sensor data is provided to a processing unit of the vehicle. The processing unit determines a distance sensing result for each location of the at least one location. The processing unit controls at least one actuator to move at least one boom of the vehicle. At least one weed control unit is attached to the at least one boom. The processing unit controls the at least one actuator to move the at least one boom on the basis of the distance sensing result for each location of the at least one location.

The present disclosure relates generally to vegetation management and control, in particular, to vegetation data capture, maintenance workflow generation, prioritization, passive and continuous monitoring of vegetation, and predictive analysis for vegetation that may be within or adjacent to clearance zones for railway, transportation, utility, pipeline, range & pasture, and industrial sites.

An improved groove and crack cleaning tool that is economical in cost to manufacture, includes a rigid blade head with a blade tip at the end of the blade edge adapted to dislodge debris build-up commonly found between outdoor surfaces. In addition, groove and crack cleaning tool has a handle adapter built into the blade head for the attachment of different types of handles. The blade head having different thickness and length provide a tool that is simple and easy to use on many outdoors surface and during tool operation, the blade edge glide will slide over the outdoor surface without causing damage to that surface. The blade head is angled to easily wedge under any debris lodged in groove or cracks forcing the lodged debris generally upward.

The present invention relates to an apparatus for weed control. It is described to provide (210) a processing unit with at least one image of an environment. The processing unit analyses (220) the at least one image to determine at least one location within the environment for activation of at least one mulch application unit. The at least one mulch application unit is configured to apply at least one mulch to the at least one location for weed control. An output unit outputs (230) information that is useable to activate the at least one mulch application unit.