Abstract: A method and an apparatus for detecting a road lane are provided. The method includes acquiring a current road image of a road around a vehicle and inputting the current road image into a deep learning model and detecting a road lane region in the current road image based on a result outputted from the deep learning model. The deep learning model includes a first model device and a second model device. The first model device includes at least one first model subdevice which includes a convolutional neural network and a first recurrent neural network, and the second model device includes at least one second model subdevice which includes a deconvolution neural network and a second recurrent neural network.

Abstract: The present disclosure provides a method and a device for detecting network intrusion. The method includes: obtaining a feature vector of a network flow to be detected; and detecting the feature vector using a deep neural network, and determining a network intrusion category of the network flow to be detected, in which the deep neural network is generated by training with training data, the training data includes feature vectors of normal samples and feature vectors of attack samples, the attack samples include original attack samples and generated attack samples by adding noise to the original attack samples. The method can improve an ability to identify unknown attacks and a normalization ability of known attacks.

Abstract: The present disclosure provides a method and a device for detecting network intrusion. The method includes: obtaining a feature vector of a network flow to be detected; and detecting the feature vector using a deep neural network, and determining a network intrusion category of the network flow to be detected, in which the deep neural network is generated by training with training data, the training data includes feature vectors of normal samples and feature vectors of attack samples, the attack samples include original attack samples and generated attack samples by adding noise to the original attack samples. The method can improve an ability to identify unknown attacks and a normalization ability of known attacks.

Abstract: An event detection method in a distributed environment includes, when a non-parsable event occurred during grammar parsing, executing the following process until the first grammar parser module obtains a detection result, including the event that the current grammar parser module can not parse in a scheduling request as a next event to be detected and sending it to the grammar control module, scheduling, by the grammar control module, other grammar parser module as the target grammar parser module for further parsing based on the scheduling strategy table, performing grammar parsing based on the local parsing table in the scheduled target grammar parser module, returning parsing results to the grammar control module for further parsing when no non-parsable event is found; or repeating the above process with the target grammar parser module as a new current grammar parser module when an non-parsable event is found.

Abstract: The present invention provides a method for data linkage driven by an event, used for data interaction between a first platform and a second platform. The second platform stores shared information and the method comprises: determining which platform the received event is from; forwarding a data packet from the second platform to the first platform for logical operation processing when the received event is from the second platform; when the received event is information from the first platform that at least includes a shared information operation instruction resulting from logic operation processing of data packets in the first platform, returning a shared information operation instruction completion message to the first platform, meanwhile forwarding the shared information operation instruction to the second platform so as to complete the shared information operation on the second platform. Therefore, the first platform acquires data synchronously without waiting for feedback of the second platform.

Abstract: An event detection method in a distributed environment includes, when a non-parsable event occurred during grammar parsing, executing the following process until the first grammar parser module obtains a detection result, including the event that the current grammar parser module can not parse in a scheduling request as a next event to be detected and sending it to the grammar control module, scheduling, by the grammar control module, other grammar parser module as the target grammar parser module for further parsing based on the scheduling strategy table, performing grammar parsing based on the local parsing table in the scheduled target grammar parser module, returning parsing results to the grammar control module for further parsing when no non-parsable event is found; or repeating the above process with the target grammar parser module as a new current grammar parser module when an non-parsable event is found.

Abstract: A barrier partitioning method and device are used for partitioning a barrier area from an image. The method includes: performing edge detecting and partitioning blocks to the image to obtain multiple edge image blocks; performing beeline detection to each edge image block to obtain beelines respectively; for each beeline, determining the line direction of the beeline corresponding to a standard road plane, and determining the edge image block to be a barrier block according to the line direction; forming all the determined barrier blocks to be a barrier area according to a connection principle.

Abstract: A method for identifying barriers in images is disclosed. In the method, images of a current frame and N frame which is nearest to the current frame are obtained, the obtained images of the frames are divided in the same way, and the image of each frame obtains a plurality of divided block regions; the motion barrier confidence of each block region corresponding to the current frame and the N frame which is nearest to the current frame is calculated; whether each block region in the image of the current frame is decided successively according to the motion barrier confidence of each block region corresponding to the current frame and the N frame which is nearest to the current frame; the barriers in the images are determined according to each block region.

Abstract: A barrier partitioning method and device are used for partitioning a barrier area from an image. The method includes: performing edge detecting and partitioning blocks to the image to obtain multiple edge image blocks; performing beeline detection to each edge image block to obtain beelines respectively; for each beeline, determining the line direction of the beeline corresponding to a standard road plane, and determining the edge image block to be a barrier block according to the line direction; forming all the determined barrier blocks to be a barrier area according to a connection principle.

Abstract: The embodiments of the present invention disclose an event detection method and device. The method includes: predefining event-based detection rules with a predicative context-free grammar; generating by parsing the detection rules a parsing table of pushdown automaton which supports parallel parsing; receiving an event to be detected; and analyzing by a controller the event to be detected according to the parsing table, to obtain a detection result. The present invention is especially applicable to detection of network attack events. The embodiments of the present invention detect the attacks with a predicative context-free grammar on the basis of events, and ensure a close combination of a protocol parsing process and an attack detection process, as well as a close combination of multiple attack detection rules, thus decreasing unnecessary calculations.