Object Detection MCQ · test your knowledge
From bounding boxes to YOLOv8 – 15 questions covering anchor boxes, NMS, mAP, and modern detectors.
Object detection: locate and classify
Object detection combines classification and localization. Models predict bounding boxes and class labels for multiple objects in an image. This MCQ covers both one‑stage (YOLO, SSD) and two‑stage detectors (Faster R‑CNN), anchor mechanisms, evaluation metrics (mAP), and post‑processing like Non‑Maximum Suppression (NMS).
Why object detection matters
From autonomous vehicles to medical imaging, object detection powers countless applications by providing spatial understanding of scenes.
Object detection glossary – key concepts
Bounding box
Rectangular region defined by (x, y, width, height) or (x1, y1, x2, y2) that encloses an object.
Anchor boxes
Predefined boxes of various scales/aspect ratios used as references for predicting object locations.
YOLO (You Only Look Once)
One‑stage detector that treats detection as a regression problem, extremely fast.
SSD (Single Shot Detector)
One‑stage detector using multi‑scale feature maps for predictions.
Faster R‑CNN
Two‑stage detector: Region Proposal Network (RPN) then classification/regression heads.
Non‑Maximum Suppression (NMS)
Post‑processing to remove duplicate detections based on IoU and confidence.
mAP (mean Average Precision)
Primary metric for object detection, averaging precision across IoU thresholds and classes.
IoU (Intersection over Union)
Measures overlap between predicted and ground‑truth boxes.
# IoU calculation (NumPy style)
def iou(box1, box2):
x1 = max(box1[0], box2[0])
y1 = max(box1[1], box2[1])
x2 = min(box1[2], box2[2])
y2 = min(box1[3], box2[3])
inter = max(0, x2-x1) * max(0, y2-y1)
area1 = (box1[2]-box1[0])*(box1[3]-box1[1])
area2 = (box2[2]-box2[0])*(box2[3]-box2[1])
union = area1 + area2 - inter
return inter / union
Common object detection interview questions
- What is the difference between one‑stage and two‑stage detectors?
- How do anchor boxes help in detecting objects of different shapes?
- Explain Non‑Maximum Suppression and why we need it.
- What is mAP and how is it calculated for object detection?
- How does YOLO perform detection in a single pass?
- What is the role of the Region Proposal Network in Faster R‑CNN?