Object detection method and system

A system for object detection, comprising:

• a first neural network system comprising:
• a feature extraction subnetwork configured to acquire a current frame of a sequence of frames representing an image sequence and extract a feature map of the current frame;
• a time domain pooling subnetwork configured to pool the feature map of the current frame with information of a pooled feature map of a previous frame to thereby obtain a pooled feature map of the current frame;
• and
• a detection subnetwork configured to detect an object from the pooled feature map of the current frame;
• a second neural network system configured to detect objects from the sequence of frames, the second neural network system comprising a long and short term memory (LSTM) network or a sequence non-maximum suppression (Seq-NMS) network;
• wherein the first or second neural network system is configured to determine object movement speed, and if the object movement speed is above a threshold, object detection results for the second network system are used for a final object detection result, and if the object movement speed is below the threshold, object detection results for the first neural network system are used for the final object detection result.

An electronic apparatus comprising:

• an event camera;
• and
• an object detection system including at least one processor executing instructions to:
• acquire from the event camera a current frame among event frames generated by the event camera;
• extract a feature map of the current frame;
• pool the feature map of the current frame with information of a pooled feature map of a previous frame to thereby obtain a pooled feature map of the current frame, wherein the pooled feature map of the previous frame is generated through recursive application of a plurality of pooled feature maps of respective prior frames;
• and
• detect an object from the pooled feature map of the current frame,
• wherein:
• the object detection system is a neural network system, and the electronic apparatus further comprising at least one of a long and short term memory (LSTM) network and a sequence non-maximum suppression (Seq-NMS) network;
• and
• the at least one of the LSTM and Seq-NMS network is configured to receive the event frames from the event camera and determine therefrom object movement speed;
• wherein if the object movement speed is above a threshold, object detection results for the LSTM or Seq-NMS network are used for a final object detection result, and if object movement speed is below the threshold, object detection results for the neural network system are used for the final object detection result.