Ranging method and apparatus, robot, and storage medium

A robot, comprising a first image collection apparatus, a second image collection apparatus, a processor and a memory, wherein the memory stores computer program instructions capable of being executed by the processor, and when executing the computer program instructions, the processor is configured to:

• determine, in response to identifying an object to be measured from a first image collected by the first image collection apparatus, a first distance of the object relative to the self-mobile robot, wherein content in the first image comprises at least the object and a surface on which the object is located;
• select a point located on the object from the first image as a reference point;
• determine initial parallax based on the first distance;
• and determine, based on the initial parallax and a preset parallax range, a region of interest from a second image collected by the second image collection apparatus, and determine a location of the reference point from the region of interest as a first target point;
• determine a second target point from the region of interest based on the first target point, and determine an actual parallax distance between the first image collection apparatus and the second image collection apparatus by using a location of the second target point;
• and
• calculate depth information of the object based on the actual parallax distance.

A non-transitory computer-readable storage medium, storing computer program instructions, wherein when the computer program instructions are invoked and executed by a processor, a ranging method is implemented, wherein the ranging method comprises:

• determining, in response to identifying an object to be measured from a first image collected by a first image collection apparatus, a first distance of the object relative to the self-mobile robot, wherein content in the first image comprises at least the object and a surface on which the object is located;
• selecting a point located on the object from the first image as a reference point;
• determining initial parallax based on the first distance;
• and determining, based on the initial parallax and a preset parallax range, a region of interest from a second image collected by a second image collection apparatus, and determining a location of the reference point from the region of interest as a first target point;
• determining a second target point from the region of interest based on the first target point, and determining an actual parallax distance between the first image collection apparatus and the second image collection apparatus by using a location of the second target point;
• and
• calculating depth information of the object based on the actual parallax distance.