refactor: remove unused multi-preprocessing code and configurations

- Remove ENABLE_MULTI_PREPROCESSING, ENABLE_CONTRAST_ENHANCEMENT, ENABLE_SHARPENING, ENABLE_ULTRALYTICS_PREPROCESSING flags
- Delete detectWithMultiplePreprocessing() method (complex parallel execution)
- Delete enhanceImageForDetection() method (CLAHE contrast enhancement)
- Delete applySharpeningFilter() method (convolution sharpening)
- Delete preprocessOriginalStyle() method (simple resize)
- Simplify detectWithPreprocessing() to only use ultralytics standard preprocessing
- Remove method parameter since only one preprocessing approach is used
- Clean up orphaned comments and documentation

This removes ~150 lines of unused code while maintaining 100% functionality.
Single ultralytics preprocessing provides good accuracy at 640x640 resolution
for small UI elements like pokeballs and shiny icons.

Related todos: #remove-unused-multipass

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

app/src/main/java/com/quillstudios/pokegoalshelper/ml/YOLOInferenceEngine.kt

@@ -44,8 +44,7 @@ class YOLOInferenceEngine(
         private const val NUM_DETECTIONS = 300
         private const val NUM_CLASSES = 95
         
-        // Enhanced accuracy settings for ONNX (fixed input size) - WITH PER-METHOD COORDINATE TRANSFORM
+        // Enhanced accuracy settings for ONNX (fixed input size)
-        private const val ENABLE_MULTI_PREPROCESSING = false // Multiple preprocessing techniques - DISABLED for mobile performance
         private const val ENABLE_TTA = true // Test-time augmentation
         private const val MAX_INFERENCE_TIME_MS = 4500L // Leave 500ms for other processing
         
@@ -56,10 +55,7 @@ class YOLOInferenceEngine(
         var DEBUG_CLASS_FILTER: String? = null // Set to class name to show only that class
         var SHOW_ALL_CONFIDENCES = false // Show all detections with their confidences
         
-        // Preprocessing enhancement techniques
+        // Preprocessing enhancement techniques (single pass only)
-        private const val ENABLE_CONTRAST_ENHANCEMENT = true
-        private const val ENABLE_SHARPENING = true
-        private const val ENABLE_ULTRALYTICS_PREPROCESSING = true // Re-enabled with fixed coordinates
         private const val ENABLE_NOISE_REDUCTION = true
         
         // Confidence threshold optimization for mobile ONNX vs raw processing
@@ -222,16 +218,8 @@ class YOLOInferenceEngine(
         {
             PGHLog.d(TAG, "🎯 Starting ONNX YOLO detection...")
             
-            val detections = if (ENABLE_MULTI_PREPROCESSING)
+            // Single preprocessing method - ultralytics standard
-            {
+            val detections = detectWithPreprocessing(inputMat)
-                // Multiple preprocessing methods with parallel execution
-                detectWithMultiplePreprocessing(inputMat)
-            }
-            else
-            {
-                // Single preprocessing method
-                detectWithPreprocessing(inputMat, "ultralytics")
-            }
             
             // Update performance stats
             lastInferenceTime = System.currentTimeMillis() - start_time
@@ -249,71 +237,13 @@ class YOLOInferenceEngine(
         }
     }
 
-    private suspend fun detectWithMultiplePreprocessing(inputMat: Mat): List<Detection>
-    {
-        val futures = mutableListOf<Future<List<Detection>>>()
-        
-        try
-        {
-            // Submit different preprocessing methods using shared executor
-            if (ENABLE_ULTRALYTICS_PREPROCESSING)
-            {
-                futures.add(preprocessingExecutor.submit<List<Detection>> { 
-                    detectWithPreprocessing(inputMat, "ultralytics") 
-                })
-            }
-            
-            if (ENABLE_CONTRAST_ENHANCEMENT)
-            {
-                futures.add(preprocessingExecutor.submit<List<Detection>> { 
-                    detectWithPreprocessing(inputMat, "enhanced") 
-                })
-            }
-            
-            if (ENABLE_SHARPENING)
-            {
-                futures.add(preprocessingExecutor.submit<List<Detection>> { 
-                    detectWithPreprocessing(inputMat, "sharpened") 
-                })
-            }
-            
-            // Collect results with timeout
-            val all_detections = mutableListOf<Detection>()
-            for (future in futures)
-            {
-                try
-                {
-                    val detections = future.get(MAX_INFERENCE_TIME_MS / futures.size, TimeUnit.MILLISECONDS)
-                    all_detections.addAll(detections)
-                }
-                catch (e: Exception)
-                {
-                    PGHLog.w(TAG, "⚠️ Preprocessing method timed out or failed", e)
-                }
-            }
-            
-            // Merge and filter detections
-            return mergeAndFilterDetections(all_detections)
-        }
-        catch (e: Exception)
-        {
-            PGHLog.e(TAG, "❌ Error in multiple preprocessing", e)
-            return emptyList()
-        }
-    }
 
-    private fun detectWithPreprocessing(inputMat: Mat, method: String): List<Detection>
+    private fun detectWithPreprocessing(inputMat: Mat): List<Detection>
     {
         try
         {
-            // Apply preprocessing based on method
+            // Apply ultralytics preprocessing (only method used)
-            val preprocessed_mat = when (method)
+            val preprocessed_mat = preprocessUltralyticsStyle(inputMat)
-            {
-                "ultralytics" -> preprocessUltralyticsStyle(inputMat)
-                "enhanced" -> enhanceImageForDetection(inputMat)
-                "sharpened" -> applySharpeningFilter(inputMat)
-                else -> preprocessOriginalStyle(inputMat)
-            }
             
             return try
             {
@@ -326,7 +256,7 @@ class YOLOInferenceEngine(
         }
         catch (e: Exception)
         {
-            PGHLog.e(TAG, "❌ Error in preprocessing method '$method'", e)
+            PGHLog.e(TAG, "❌ Error in preprocessing", e)
             return emptyList()
         }
     }
@@ -474,88 +404,6 @@ class YOLOInferenceEngine(
         }
     }
 
-    /**
-     * Enhanced preprocessing with CLAHE contrast enhancement
-     */
-    private fun enhanceImageForDetection(inputMat: Mat): Mat
-    {
-        val enhanced = Mat()
-        try
-        {
-            // Apply CLAHE for better contrast
-            val gray = Mat()
-            val enhanced_gray = Mat()
-            
-            if (inputMat.channels() == 3)
-            {
-                Imgproc.cvtColor(inputMat, gray, Imgproc.COLOR_BGR2GRAY)
-            }
-            else if (inputMat.channels() == 4)
-            {
-                Imgproc.cvtColor(inputMat, gray, Imgproc.COLOR_BGRA2GRAY)
-            }
-            else
-            {
-                inputMat.copyTo(gray)
-            }
-            
-            val clahe = Imgproc.createCLAHE(CLAHE_CLIP_LIMIT, Size(CLAHE_TILE_SIZE, CLAHE_TILE_SIZE))
-            clahe.apply(gray, enhanced_gray)
-            
-            // Convert back to color
-            if (inputMat.channels() >= 3)
-            {
-                Imgproc.cvtColor(enhanced_gray, enhanced, Imgproc.COLOR_GRAY2BGR)
-            }
-            else
-            {
-                enhanced_gray.copyTo(enhanced)
-            }
-            
-            gray.release()
-            enhanced_gray.release()
-        }
-        catch (e: Exception)
-        {
-            PGHLog.e(TAG, "❌ Error enhancing image", e)
-            inputMat.copyTo(enhanced)
-        }
-        return enhanced
-    }
-
-    /**
-     * Apply sharpening filter for enhanced edge detection
-     */
-    private fun applySharpeningFilter(inputMat: Mat): Mat
-    {
-        val sharpened = Mat()
-        try
-        {
-            // Create sharpening kernel
-            val kernel = Mat(3, 3, CvType.CV_32F)
-            kernel.put(0, 0, 0.0, SHARPENING_EDGE_VALUE, 0.0, SHARPENING_EDGE_VALUE, SHARPENING_CENTER_VALUE, SHARPENING_EDGE_VALUE, 0.0, SHARPENING_EDGE_VALUE, 0.0)
-            
-            // Apply filter
-            Imgproc.filter2D(inputMat, sharpened, -1, kernel)
-            
-            kernel.release()
-        }
-        catch (e: Exception)
-        {
-            PGHLog.e(TAG, "❌ Error sharpening image", e)
-            inputMat.copyTo(sharpened)
-        }
-        return sharpened
-    }
-
-    /**
-     * Original style preprocessing (simple resize)
-     */
-    private fun preprocessOriginalStyle(inputMat: Mat): Mat
-    {
-        return safeResize(inputMat, Size(config.inputSize.toDouble(), config.inputSize.toDouble()))
-    }
-
     /**
      * Letterbox resize maintaining aspect ratio with gray padding
      */